Expanding Innovation in Agriculture: Case Study on Adoptable Technologies Using GenAI Based on Traditional Knowledge Management

You’re listening to “Expanding Innovation in Agriculture: Case Study on Adoptable Technologies Using GenAI Based on Traditional Knowledge Management,” by D.I. Contreras-Medina and colleagues. Published in 2025.

Abstract.

Given the demand for more and better food by 2050, the use of technologies in agricultural activities is the most appropriate way to strengthen the sector; however, their adoption remains a milestone for small-scale agriculture. Currently, GenAI, established as a tool to facilitate orga- nizational adaptability in dynamic environments, has been integrated into industry, education, and medicine, and it is time to enable technological adoption in agricultural settings.

Therefore, considering a combination of chain sampling and judgmental sampling methods, including 24 small-scale producers and nine studies, through roadmapping and qualitative prompt methodologies, in addition to social and productive characteristics, this study combines GenAI with the characterization of traditional knowledge management to design a proposal for adopt- able technologies for small-scale pipiana pumpkin producers in Mexico, involving researchers in the region. The results expand on technologies aligned with the experience, skills, and practices embedded in the sowing–harvest circuit and in initial crop disposal. The research data may interest researchers, policymakers, and associations interested in combining technology and TK for agricultural development as a novel way of characterizing them; however, its applicability must be verified.

Academic Editors: Thuseethan Selvarajah and Yakub Sebastian Received: 18 October 2025 Revised: 3 December 2025 Accepted: 8 December 2025 Published: 10 December 2025

1. Introduction.

Given the growing demand for more and better food by 2050, the integration of innovation is the most recommended option for strengthening the global agricultural sector. The intersection of technology and farming activities has converged in robots, drones, and artificial intelligence as part of the 21st-century evolution. However, its adoption remains a milestone for small-scale agriculture.

Small-scale agriculture, as the base of the food chain, is responsible for producing 30% of total crop production and is today called upon to increase its contribution by more than double to feed a population projected to grow by around 70% by 2050. In the context of social, economic, and technological constraints, amid a changing environment, small-scale

agricultural farmers have endured, utilizing their only available resource: knowledge, which has been established as a crucial asset for achieving sustainability.

The Generative Artificial Intelligence GenAI, classified as a tool for solving sustain-ability challenges, also facilitates the adaptability of organizations immersed in a dynamic environment. Ranked as the most important emerging technology in 2023, GenAI is studied to improve capabilities across diverse areas. For example, ref. shows the applications of GenAI in image analysis to improve safety in industries. Ref. describes the current status of GenAI in marketing organizations. Ref. exposes the integration of GenAI as a strategy in higher education institutions. Ref. mentions that GenAI has the potential to enhance management and innovation in the fields of medicine and healthcare.

The above demonstrates that GenAI is developing solutions across diverse paradigms and fields; however, its contribution to addressing the challenge of technological adoption in small-scale agriculture remains pending. This is important because technologies are aimed at dynamizing agricultural activity, while the integration of GenAI with endur-ing traditional knowledge (TK) of small-scale farmers can generate robust solutions for addressing food security and sustainable agriculture.

Based on the assertion that integrating traditional knowledge with technology can promote inclusiveness and inspire the application of innovation, this study has as its objective to design an adaptable technological proposal based on TK using GenAI, following the following hypothesis:

TK’s integration with GenAI will expand technological options for pipiana pumpkin H1. small-scale producers.

Because the application of knowledge is a significant area of research in artificial intelligence, this paper contributes to the design of an adaptable technological proposal based on TK using GenIA. So, this study follows the following research questions:

How can GenAI be associated with small-scale farmers’ TK?

What technologies can be adopted into the agricultural practice based on the associa-tion of GenAI with farmers’ TK?

Therefore, the study of GenAI is presented as an element to facilitate the adoption of technologies in small-scale agriculture. The characteristics of GenAI prompt included qualitative elements that reflect the nature of the TK, drawing on the experience, practice, and skills of small-scale producers embedded in the sowing–harvest–first sale circuit of pipiana pumpkins in Mexico. In addition, since the social and productive characteristics surrounding production were considered essential for the adoption of technologies, its conjunction still needs to be proven.

2. Literature Review.

In agricultural activities, the successful deployment of technologies depends on the farmers adoption. This means that innovation must be centered on human beings and used in the production process; however, most small-scale farmers are unaware of it.

Historically, there may be many reasons for the non-adoption of technologies. For example, ref. reveals that innovation does not address the problem; Ref. exposes the complexity of innovation; Ref. highlights the socio-cultural barriers; And reveals the characteristics and perceptions of farmers regarding technology. For this reason, it is essential to enable technology that meets the needs, particularities, perceptions, and environment in which agricultural practices are developed.

To promote technology, the literature has documented numerous proposals for in-tegrating it into agriculture. For example, ref. proposes the Living Lab as a tool for detecting innovation needs through collaboration among agricultural stakeholders in Italy, which has led to knowledge of automated and intelligent irrigation systems, drones, and sensors. Ref. highlights the Program for Agriculture Transformation and Increased Incomes (UP Accelerator PRAGATI) as a platform for proposing innovations that combine global expertise with local knowledge in India, resulting in the development of seed va-rieties and precision irrigation technology. Ref. discusses how, through the Elevate Program, innovative ideas are identified, germinated, and piloted to benefit poor farming communities.

Recently, drones have been introduced in Asia for virus detection, flies have been used to reduce food waste in Africa, and training has been provided to create added value from fish skin in Cape Verde. Additionally, ref. proposes apps and computing technology; Ref. proposes collaborative platforms; Ref. proposes blockchain tech-nology; And proposes credit based on trust and mechanical seeders. However, from the TK perspective, innovations enabled by GenAI are still pending.

GenAI, born out of the need for food security, can process both quantitative and qualitative data and generate new data based on context. Its AI Large Language Model (LLM) has led to the creation of IA assistants that perform in-depth explorations using and analyzing current data across different platforms, such as Google’s Gemini.

In the literature, the integration of AI in agriculture is based on a quantitative analysis of elements for the improvement of activity. For example, ref. presents examples of the use of AI in the agrifood sector, including data types and numbers of insects for pest management, genetic data for genetic improvement, and information on moisture levels and nutritional deficiencies to inform decisions. Ref. combines IA with Geographic Information Systems and Global Positioning Systems, incorporating soil, climate, and historical crop data to improve agricultural practices. Ref. presents success stories in which soil data, crop status, and genomic information are integrated to increase agricultural productivity.

The above demonstrates the integration of AI with objective data; however, combining AI with qualitative elements, such as experience, skills, or practices embedded in farmers’ TK, remains unexplored.

With its ability to articulate the present through the wisdom of the past to support future ways of life, TK has been part of human life for hundreds of thousands of years. In agricultural activities, TK is embedded in the practices of around 2000 million small-scale farmers worldwide, and its use could change future agricultural productivity, promoting, in parallel, the adoption of technology.

In this regard, TK is worth studying for various purposes. For example, in the study by, which examines phenomena related to vegetation, astronomical, or animal behavior, it shows how farmers adapt strategies that favor their crops in the face of climate change. Ref. considers the interaction of the agricultural productive ecosystem and proposes strategies for coffee production that support social, economic, and environmental sustainability. Ref., combining TK, scientific knowledge, civil society, business, and government, under a line of co-production, proposes sustainable ocean management within the framework of the United Nations Ocean Decade platform.

In Mexico, the study of TK has developed from different angles (see Table 1):

In any case, TK should be represented as an expression of the perception of knowledge-holders within a specific productive practice, integrating their current social and productive situation as well as their adaptive strategies, to contribute to science and technology; otherwise, the gap between technology and agriculture will widen, distancing production levels from the growing population.

This paper begins with an introduction that outlines the problems and needs of GenAI and TK by posing research questions, followed by a literature review that explores existing studies in GenAI and TK and records the working hypothesis. The third part details the methodology used to integrate GenAI and TK, followed by the results on adoptable technologies. This is supplemented by a discussion comparing existing studies on the topic and concludes with conclusions and future research directions.

3. Materials and Methods.

The present case study integrates GenAI with TK of 24 small-scale producers of pipiana pumpkin in addition to nine people dedicated to the research in Mexico. The farmers’ sample was chain-like, taking advantage of the interaction between women and men engaged in the activity, whereas, for the researchers, it was a judgment based on the criteria of those developing research in the agricultural sector. Both were conducted sequentially. GenAI was used on the Gemini platform as an open Generative Ar-tificial Intelligence system.

At the same time, TK considered the experience, practices, and skills of farmers from the localities of Atliaca, Atocutla, and Mochitlan in the mu-nicipalities of Tixtla de Guerrero, Ayutla de los Liebres, and Mochitlan, respectively, in Guerrero; as well as Bolonchén de Rejón and Ich-Ek in the city of Holpelchén in Campeche, Mexico, which were characterized through roadmapping by being considered as a knowl-edge management methodology. These municipalities account for 24.61% of the planted area, totaling 4557.74 hectares, and 18.78% of the total production, equivalent to 3271.89 tons. Regarding the researchers, it was considered that they were part of the National System of Research of Secihti (Secretaria de Ciencia, Humanidades, Tecnología e Innovación, acronym in Spanish) recognized for their scientific and technological work.

The combination of GenAI and roadmapping as a knowledge management element is based on the premise that a technological proposal can be generated from TK analysis.

Contact with small-scale farmers was made through the representative of the mezcal product system in the State of Guerrero. In Campeche, support was provided by the project’s technical manager, while, with the researchers, it was extended through direct invitations and through the coordinators of an educational program. In both cases, the study and its objective were explained to obtain their acceptance and informed consent. Information on small-scale producers was collected through face-to-face and field visits, using questionnaires over 3 years, while the researchers’ data was collected through online questionnaires over another year during the period 2019–2024. The technological proposal was made using GenAI. The study comprised three phases:

First phase: To represent the TK and integrate it into GenAI, its elements of experience, practice, and skills were divided into three stages:

Stage 1. The experience was characterized by problems, expectations, and strategies to improve the planting and harvesting processes, as well as the initial disposal of pipiana squash. This representation is based on the fact that TK practice involves how small-scale producers confront and solve problems, based on the wisdom of the past. To obtain the information, the roadmapping methodology, a knowledge management approach used in the agricultural context through interaction, was employed following the scheme’s logic, applying three key questions and keeping in mind problems, expectations, and strategies. The following questions were formalized: a. In the sowing–harvesting–first disposal practice of pipiana pumpkin, what are your current problems or expectations?

b. What strategies could be developed to improve the sowing –harvesting–first disposal practice of the pipiana pumpkin?

Stage 2. In practice, the activities carried out within the planting–harvesting and the first disposal circuit of the pipiana pumpkin. Mentzer’s supply chain concept was employed, utilizing face-to-face interviews and field visits to examine the producer– customer flow. The following question was reviewed: a. In the production of pipiana pumpkin, what are the activities of the planting–harvest– first sale circuit?

Stage 3. In skills, referred to as the forms of management and development of the farm, were collected productive and social elements embedded in the pipiana pumpkin circuit and that are important for the implementation of technologies. For this, educational level, age, family members, male–female ratio in the activity, crop area, planting other crops, food use, sale price per kilogram, and consumption methods were collected, under the following question: a. In the production of pipiana pumpkin, what are the social and productive elements of small-scale producers?

Second phase: For the use of GenAI and determining the technologies that could be adopted, the qualitative nature of TK was taken into account. For this reason, the recommendations of, on the design of prompts for qualitative analysis, were considered and formalized as follows: a. Considering the social and productive information (background) and using the TK elements (analytical process), it was analyzed and developed a proposal for adoptable technologies to improve the sowing, harvesting, and first disposal circuit of pipiana pumpkin (goal of the task and output). Please, prioritize TK elements (prioritization).

The information was previously prepared and documented by the State and munici-pality, beginning with data on the social and productive context, followed by elements of TK (inputs, transparency, and traceability), while role-playing and acknowledgement of expertise were established, considering the research perspective.

The prompt sequence was pre-trained using parameters related to technological rec-ommendations in Spanish for improving the production of pipiana pumpkin. The number and logic of training iterations were 5, covering climate, rainfall, and crops, and recom-mending, in Spanish, technological strategies to combat pests. Following this, agreement prompts were introduced in the same line, attaching information by State and municipality, performing 5 more iterations.

Third phase: To reduce the bias in the results, the GenAI technological proposal was sent to different researchers for critical review, with the aim of either rejecting or validating it. If the proposal was approved, it was also requested to be ranked from the most adoptable technology to the least within the planting–harvesting–first disposal practice for the pipiana pumpkin. If the proposal was rejected, the proposer was requested not to respond (see Figure 1).

The proposal was sent to 12 researchers collaborating in the doctoral program in engineering sciences at TecNM in Celaya, of whom 9 responded via the SurveyMonkey platform to researchers affiliated with the National System of Researchers in Mexico who have experience in technology within the agricultural context.

The criteria for evaluating the proposal involved recording the information obtained from the TK, practice, and skills of the small-scale producers, including the technologies proposed by the GenAI in each of the five regions, and asking them to order them in the following sequence: 1 totally adoptable, 2 moderately adoptable, 3 somewhat adoptable, and so on.

The Ultra 1.0-2.0 version from Gemini and its configuration were via prompts. The number and logic of training iterations were 5, exemplifying the situation of climate, rainfall, and crops, and recommending technological strategies to combat pests in Spanish. Following this, agreement prompts were introduced in the same line, attaching information by State and municipality, performing 5 more iterations.

Information Analysis and Validity

The results were registered, analyzed, tabulated, ordered, and coded from the most frequently chosen to the least, according to the recommendations of, using IBM SPSS Statistics v21 to perform descriptive statistics, while Visio v2016 was used to create figures.

Reliability and validity were established through the research of applied to the agricultural context.

The identity of small-scale producers of pipiana pumpkin from Guerrero and Campeche was validated by the representative of the mezcal product system and the project’s technical manager. The identities of the researchers who analyzed the proposal were validated by those involved in the project.

4. Results.

4.1. Traditional Knowledge of the Pipiana Pumpkin.

TK is embedded in the small-scale producers of pipiana pumpkin, specifically in the experience, presenting different problems, expectations, and strategies for improving the circuit in Guerrero and Campeche.

In Guerrero:

• The Atliaca community in Tixtla de Guerrero focuses on addressing the problems of water scarcity and pest infestations. The expectations are to increase productivity and profitability, as well as to improve land and crop management. The strategies include exploring new areas for planting and expanding market access.

• Atocutla, the community of Tixtla de Guerrero, faces a lack of market and the under-utilization of pumpkin resources as problems. The expectation is for production with reduced pest presence. The strategy is fertilizers.

• Mochitlán, as the municipal capital, faces problems with pest infestations and limited market access. The expectation is to increase production by increasing the number and volume of plants, while the strategy is expert advice.

In Campeche:

• In the Bolonchén de Rejón community of Holpelchén, the problem is the presence of pests. The expectations are that technological development will increase crop production and expand access to government support, while the strategy focuses on greater crop profitability.

• The Ich-Ek community in Holpelchén also faces pest problems. The expectation is to increase crop profitability and pumpkin utilization, while the strategy is to increase the number of plants (see Figures 2 and 3).

In the practice, the activities of the sowing–harvest–first sale circuit of pipiana pumpkin begin with the removal of other plants; sowing the seeds; fertilization; foliar application; the harvesting of the pumpkin; and the selling of the seeds (see Figure 4).

The skills related to social and productive elements vary by locality, with each present-ing its particular strengths in the planting, harvesting, and first sale of pipiana pumpkins. In Guerrero, the skills are:

• In Atliaca, producers have not completed elementary school, are 51 years old, have eight family members, with a proportion of 34% male and 66% female, have a crop area of 5 hectares. Additionally cultivate beans and corn, sell the seed for food and fertilizer for USD 0.80, and have pumpkin atole and nixtamal to make tortilla, besides water and mole as consumption methods.

• In Atocutla, producers have completed elementary school with 67 years of experience, have eight family members, with 50% male and 50% female representation, cultivate a 1.5-hectare crop area, with corn as an additional crop. They sell the seed for USD 1.45 and consume it fried, with milk, or in atole.

• In Mochitlán, producers also have an elementary school educational level, are 40 years old, have seven members in their families, a proportion of 10% male and 90% female, cultivate 2 hectares, have corn as an additional crop, sell the seed for USD 2.68, and the consumption is made as a pumpkin and seed candy. In Campeche, the skills are:

• Bolonchén de Rejón producers have an elementary school education, are 44.5 years old, have six members in their families, cultivate 12.5 hectares of crop area, and engage in corn and honey production as additional activities. They sell the seed at USD 1.87, and the seed can be consumed fried, in soup, or as a snack.

• In Ich-Ek, producers have an elementary school education, are 60 years old, have six family members, and cultivate 6 hectares of crops. They also engage in additional activities, such as corn and tomato farming, selling seeds, and consuming them in soup or as snacks (see Table 2).

4.2. Technologies Proposal Using GenAI.

For each location, the GenAI generates technological proposals tailored to the specific characteristics of the TK-embedded pipiana pumpkin producers in each region. In Guerrero:

• In Atliaca, the technologies are: Technologies for efficient water management such as drip irrigation, solar irrigation systems, humidity sensors, tensiometers, touch method, water conservation practices, and mulch. Pest management technolo-gies such as crop rotation, spacing between plants, residue removal, use of resistant varieties, irrigation management, weed control, mulch, balanced nutrition, use of ben-eficial fungi, harnessing bacteria, introduction of predatory insects, use of drones and remote sensors, use of traps, and manual pest removal. Technologies to improve soil fertility, such as regenerative agriculture practices and minimum tillage, use of compost and vermicompost, low-cost soil analysis (e.g., touch method), and planting of associated crops (milpa).

Technologies for market access and marketing, such as the use of digital platforms for marketing and strengthening agricultural cooperatives for negotiating power.

These technologies are linked to producers who did not complete elementary school, are 51 years old, have eight family members, mostly women, and have an area of 5 ha. • In Atocutla, the technologies are: Pest monitoring technologies such as the use of sticky traps, pheromone traps, mobile applications for pest detection through photography, digital systems for sending pest alerts, installation of environmental sensors, implementation of drone surveillance to detect changes in temperature, vege-tation, etc., and artificial intelligence advice through data for the creation of strategies.

Market access technologies, such as the use of digital markets and e-commerce plat-forms for direct sales, leveraging tools such as WhatsApp, and the use of blockchain technology to connect other actors in the chain.

The technologies are linked to producers who completed primary school, are aged 67, have eight family members, have an equal proportion of men and women, and have an area of 1.5 ha.

• In Mochitlán, the technologies are: Pest management technologies such as crop habitat sanitation, the use of resistant varieties, the adjustment of planting time, and planting of cover crops. Technologies for the monitoring and early detection of pests, such as the use of solar monitoring systems for insect tracking, the use of pheromone traps, the use of AI-powered drones for identifying pest outbreaks, the use of IoT sensors for real-time environmental data collection, and the use of mobile applications for pest monitoring and alerts.

Mechanical biological control tech-nologies such as the use of fungal formulations for pest control, the introduction of insects for pest control, the application of mycorrhizal fungi for nutrient absorption, the creation of floating covers for insect exclusion, the practice of crop staking for soil elevation, the introduction of trap crops for pest attraction, and the use of drones for pesticide application. Market access technologies, such as introducing e-commerce through platforms, implementing digital marketing through websites, and strengthen-ing agricultural cooperatives to provide negotiating power.

Agricultural extension and remote consultation technologies, such as the introduction of digital agricultural extension services for real-time consultation, the use of mobile applications for pest and price monitoring, the use of apps for video and data consultations, online training, and capacity building on finance, plant, and management, etc.

These types of technologies are linked to producers who completed primary school, are 40 years old, have eight family members, mostly women, and have an area of 2 ha. In Campeche:

• In Bolonchén de Rejón, the technologies are: Integrated pest management technolo-gies such as weed control, pest monitoring, planting time adjustment, crop rotation, insect introduction for pest control, chemical intervention for pest control, and the integration of pest management platforms. Technologies for optimizing cropping practices, such as polyculture practices, increasing foliar fertilization, and pruning and staking practices. Precision agriculture and smart farming technologies, such as the introduction of IoT sensors to understand soil conditions, climate, and crop health, and the introduction of blockchain for food traceability.

The technologies are linked to producers who completed primary school, are aged 44.5 years, have six family members, and have an area of 12.5 ha.

• In Ich-Ek, the technologies are: Technologies for integrated pest management, such as the use of IoT sensors and smart traps for pest detection and capture, an AI application for diagnosis and treatment, and the use of drones for early pest detec-tion. Sustainable control technologies such as insect introduction for pest control, precision spraying for region-specific chemical application, the use of pest-resistant varieties, weed control, crop rotation, plant selection, and the use of improved seeds. Technologies for yielding improvement and optimization, such as seed density optimization, precision planting, seed robots to ensure optimal seed placement and density, and the use of IA and algorithms for optimized spacing to optimize water, nu-trients, and crop rotation.

Technologies for precise nutrient and water management, such as the introduction of smart irrigation systems and soil moisture sensors, and automated nutrient delivery (fertigation) to precisely inject or transport water-soluble nutrients before they reach plants. Controlled environment technologies, such as the introduction of hydroponics and aeroponics, the use of improved seed varieties, technologies for water utilization and value generation, such as the introduction of advanced pulp processing techniques to create a wide range of industrial applica-tions, such as confectionery, beer, and various beverages, the introduction of drying technologies for preservation to extend the shelf life of pumpkin pulp and reduce volume and weight, and the practice of extraction of high-value biocomposites.

Technology for the diversification of value-added products, such as pumpkin flour production through the cutting and dehydration of pumpkin waste, snack production, washing, trimming, and slicing the pumpkin, beverage production using blender tanks, pasteurizers, and potential for animal feed using the waste (see Figure 5). These types of technologies are linked to producers who completed primary school, are 60 years old, have six family members, and own a 6-hectare property.

Visualizing the proposed technologies provides an opportunity to adopt some of those that would be more practically accessible to others. For example, the cover crops, crop rotation, weed control, planting period adjustment, the use of resistant varieties, and the introduction of predatory insects, in addition to strengthening the cooperatives’ bargaining power, are established before and after the application of GenAI, since they are practices within the activity and can continue to be practiced; however, some would be complicated to implement, such as the use of sensors, while others are possibly unknown to producers, such as the use of drones or aeroponics.

4.3. Technology’s Introduction.

According to the researchers’ responses, the most adoptable technologies would vary in their introduction:

In Guerrero:

• In Atliaca, the introduction would begin with pest management technologies, followed by technologies for efficient water management, technologies for market access and marketing, and technologies to improve soil fertility.

• For Atocutla, it begins with market access technologies, followed by pest monitoring technologies.

• In Mochitlán, the approach starts with technologies for the monitoring and early detection of pests, followed by pest management technologies, mechanical and biolog-ical control technologies, market access technologies, and agricultural extension and remote consultation technologies.

In Campeche:

• In Bolochén de Rejón, the introduction should begin with technologies for optimizing cropping practices, followed by the integration of pest management technologies, and precision agriculture and smart farming technologies.

• In Ich-Ek, the approach begins with integrated pest management technologies, fol-lowed by precise nutrient and water management technologies, yield improvement and optimization technologies, sustainable control technologies, technologies for water utilization and value generation, controlled environment technologies, and technologies for diversifying value-added products (see Figure 6).

In summary, the findings of this research identified three core themes. These are summarized in Table 3.

Pest management technology is a constant priority for communities in Guerrero. It is observed that, for Mochitlán, with a sale price of USD 2.68, with a proportion of 10% men versus 90% women, with an age of 40 years, technologies such as sanitation of the habitat of the crops, the adjustment of planting time, and cover crops, as proposed by the GenAI, could be implemented manually. This may be due to the community’s proposed expert advisory strategy. The same rationale could apply to agricultural extension technologies and remote consultation, as this is the only location that has this recommendation.

For the communities of Campeche, pest management is also a priority. It is noted that technologies such as sensors and smart traps, drones, and AI are recommended for areas of 6 hectares, for producers with a primary education and who are 60 years of age. This is part of the strategy to increase the number of Ich-Ek plants. In contrast, for Bolonchén de Rejón, the most profitable strategy envisions technologies such as weed control, pest monitoring, adjusting planting time, crop rotation, integrating insects, chemical intervention, and integrating platforms for pest management on areas larger than 12 hectares for 44.5-year-olds with a primary education level.

Within the study areas, sustainability and technologies for diversifying product added value are explicitly evident among Ich-Ek producers aged 60 years, with 6 hectares, and with a primary school education level. Mechanical biological control technologies are used in Mochitlán at a selling price of USD 2.68 by a group comprising 10% men and 90% women, with an average age of 40. Meanwhile, market access, such as the use of online platforms and the strengthening of cooperatives to increase their bargaining power, is found in predominantly female communities, with farms ranging from 1.5 to 5 hectares and prices ranging from USD 0.80 to USD 2.68.

5. Discussion.

This case study highlights the complexities of agricultural activity. Given its particular-ities, TK embedded in small-scale producers involves different problems, expectations, and strategies, and the introduction of technologies is proposed accordingly in each situation. This is consistent with, which highlights various problems related to soil, climate, and desertification, as well as technological strategies, such as drip irrigation, pest control, and meteorological prediction, adopted in different parts of the world.

From the conjunction of GenAI and TK, the proposal addresses the adoption of technologies for small-scale producers, including pest management technologies, biological control, precision agriculture, sustainable control, water management, and market access. It is essential to mention that the proposal includes affordable technologies that can improve the pipiana pumpkin cycle almost immediately. For example, the use of resistant varieties, the introduction of predatory insects, crop rotation, cover crops, weed control, and the adjustment of planting periods, in addition to strengthening the cooperatives’ bargaining power, could positively impact seed sowing, fertilization, foliar application, and seed sales. This sample leaves aside the infrastructure and connectivity as limitations in agricultural activity; additionally, it aligns with strategies for biological pest control.

In this sense, the literature indicates that a significant portion of these technologies, such as digital marketing, is already being utilized in agricultural activities, although not widely.

The predominance of women in agricultural activities necessitates a restructuring of how technology is adopted, emphasizing a female perspective and applying expert support as a key strategy and outcome of this study. This aligns with, which states that women may find certain technologies difficult to implement or that extension services are not adapted to their needs.

Regarding the introduction of technologies for pest management and market access, as recommended by researchers, various institutions, such as the FAO, offer affordable programs and activities, including integrated pest management and dialog spaces for small farmers.

The expansion of innovation in agriculture using GenAI proposes considering afford-able technologies for small farmers and their TK within the pipiana pumpkin circuit. This is evident with the introduction of predatory insects and the use of traps as biological control; crop rotation, cover crops, associated plants or adjusting cultivation times are proposals that expand the options recorded by, in their proposal of a smart irrigation system, crop monitoring system, and fertilizer administration, crop yield prediction, crop diseases detection, weed detection and soil management, cloud computing and big data technology; artificial intelligence and machine learning integrated in vehicles; or the use of IoT through smart irrigation or agricultural drones (see Table 4).

Despite the above, it is essential to consider the limitations of combining GenAI and TK. First, the constant development of GenAI, and second, its evolving operational methods (e.g., cost), mean that the present study represents a snapshot of TK among small pumpkin producers and may not necessarily apply to other crops. This aligns with the observations of, who stated that the evolution of AI and its uses must be considered within a specific time and context and cannot be generalized.

Policy/Practice Implications

Technology adoption has changed towards the specific characteristics of each region. Today, policies and practices must be designed and implemented according to the charac-teristics of each activity and the producers that carry them out.

Therefore, the plan to expand participation in future phases is proposed as follows: a. Consider TK’s situation, expectations, and strategies, as well as the skills and pro-cesses of the small-scale producer.

b. Pilot implementation of the top technologies by the different communities according to the sowing–harvest circuit and initial crop disposal practice.

c. Based on the above, bring expert support closer to facilitate technology adoption.

This is like what the FAO promotes when it recommends that more flexible and responsive mechanisms are needed to solve problems across the various agricultural areas of the world.

6. Conclusions.

This document presents a case study on the conjunction of GenAI and the management of traditional agricultural knowledge to generate a proposal for technologies that can be adopted by small pipiana pumpkin farmers in Mexico, taking into account their social and productive characteristics.

The combination expands the innovation with affordable proposal technologies in pest management, biological control, precision agriculture, sustainable control, water management, and market access. Plant spacing, raised planting, the touch method, and increasing producers’ bargaining power are examples that seem more achievable for small-scale producers, as they are articulated in their solution proposal and supported by expert advice. Therefore, H1 is accepted.

From the researchers’ perspective, market access technology should be considered, second only to pest management. From this perspective, it is necessary to address and strengthen pipiana pumpkin planting and harvesting, while also improving initial sales.

The results should be interpreted with caution, as the sample of small-scale producers is likely small and quantitative data are lacking (over 95% of the sample). Costs and returns are recognized as limitations, so this study could be considered a pilot. Although it may have low statistical power, it is regarded as a valuable approach for characterizing TK by combining GenAI to improve food production.

Therefore, the question, how to improve food production in regions of Africa, Asia, and Latin America?, suggests that new lines of research should involve the plan for expanding the sample in future phases, and must include the effectiveness of technologies according to the sowing–harvest circuit and initial crop disposal practice; deepen TK through situations, expectations, and strategies in addition to the skills and processes of the small-scale producers; replicate the model; understand the relation of GenAI and qualitative information; compare with other methods of LLM; and examine the cost–benefit analysis for the technology implementation according to the State, municipality, manufacturers, the chance of success, and priorities.

From an ethical standpoint, without the intention of marginalizing, modifying, or distorting the study, the integration of GenAI with TK is complementary; however, it is essential to mention that the evolution and forms of use of technology may produce different results.

The research data may interest researchers, policymakers, and associations seeking to combine technology and TK for agricultural development in the region and worldwide, providing practical value that aligns with the financial limitations of small farmers.

software, D.I.C.-M.; validation, D.I.C.-M., M.T.d.l.G.C., J.S.-G. and V.C.-R.; formal analysis, D.I.C.-M. and M.T.d.l.G.C.; investigation, D.I.C.-M.; resources, D.I.C.-M.; data curation, D.I.C.-M.; writing—original draft preparation, D.I.C.-M.; writing—review and editing, D.I.C.-M., M.T.d.l.G.C., J.S.-G. and V.C.-R.; visualization, D.I.C.-M., M.T.d.l.G.C., J.S.-G. and V.C.-R.; su-pervision, D.I.C.-M., M.T.d.l.G.C., J.S.-G. and V.C.-R.; project administration, D.I.C.-M.; fund-ing acquisition D.I.C.-M. All authors have read and agreed to the published version of the manuscript.

Funding: This research was funded by the Sectoral Research Fund in Agriculture, Livestock, Aqua-culture, Agrobiotechnology, and Plant Genetic Resources SAGARPA-CONACYT through the project “Boosting Mexican gastronomy through technological developments and strengthening the value chain for the pumpkin (curcubita species) product system”, [grant number 277781 2016] in the first phase, and the authors were funded by the APC.

Institutional Review Board Statement: Master’s Degree Review Committee in Industrial Engineering 03/MII/2025 2024-05-02.

Informed Consent Statement: Informed consent was obtained from all subjects involved in the study.

Data Availability Statement: The project can be consulted with the title “Boosting Mexican gastronomy through technological developments and strengthening the value chain for the pumpkin (curcubita es-pecies) product system”. To know the requirements, please the page the linked source transparencia/acceso-a-la-informacion/ accessed (12 June 2025).

Author Contributions: Conceptualization, D.I.C.-M.; methodology, D.I.C.-M. and M.T.d.l.G.C.;

Acknowledgments: The support of the Center for Research in Technology and Design of the State of Jalisco, A.C. (CIATEJ acronym in Spanish), as the Institution responsible for the development of the project, and the facilities of the National Institute of Technology of Mexico in Celaya (TecNM acronym in Spanish) for the continuation of the project are acknowledged. We are also grateful for the support of the Secretariat of Agriculture and Rural Development—National Council of Humanities, Sciences and Technologies (SAGARPA-CONACYT), currently designated SADER-SECIHTI (Secretariat of Science, Humanities, Technology and Innovation), for the funding received, in addition to the reviewers’ contributions: “their comments strengthened the manuscript”. During the preparation of this manuscript, the author(s) used Gemini GenAI to analyze the information.

The authors have reviewed and edited the output and take full responsibility for the content of this publication.

Conflicts of Interest: The authors declare no conflicts of interest. The funders had no role in the design of the study, in the collection, analysis, or interpretation of data, in the writing of the manuscript, or in the decision to publish the results.

1. Hamad, A.; Tayel, A.

Food 2050 Concept: Trends That Shape the Future of Food. J. Future Foods, 2025; in press. [CrossRef]

2. Aijaz, N.; Lan, H.; Raza, T.; Yaqub, M.; Iqbal, R.; Pathan, M.S.

Artificial Intelligence in Agriculture: Advancing Crop Productivity and Sustainability. J. Agric. Food Res. 2025, 20, 101762. [CrossRef]

3. Adams, A.; Jumpah, E.T.

Agricultural Technologies Adoption and Smallholder Farmers’ Welfare: Evidence from Northern Ghana. Cogent Econ. Financ. 2021, 9, 2006905. [CrossRef]

4. Ricciardi, V.; Ramankutty, N.; Mehrabi, Z.; Jarvis, L.; Chookolingo, B.

How Much of the World’s Food Do Smallholders Produce? Glob. Food Sec. 2018, 17, 64–72. [CrossRef]

5. FAO How to Feed the World in 2050.

Available online: (accessed on 21 January 2024).

Jakes, V. The Role of Traditional Knowledge in Sustainable Development. Int. J. Humanit. Soc. Sci. 2024, 3, 40–55. [CrossRef] 6.

7. Singh, K.; Chatterjee, S.; Mariani, M.

Applications of Generative AI and Future Organizational Performance: The Mediating Role of Explorative and Exploitative Innovation and the Moderating Role of Ethical Dilemmas and Environmental Dynamism. Technovation 2024, 133, 103021. [CrossRef]

8. Li, L.; Zhu, W.; Chen, L.; Liu, Y.

Generative AI Usage and Sustainable Supply Chain Performance: A Practice-Based View. Transp. Res. E Logist. Transp. Rev. 2024, 192, 103761. [CrossRef]

9. WEF Top 10 Emerging of 2023.

Available online: the linked source (accessed on 20 November 2024).

Gupta, P.; Ding, B.; Guan, C.; Ding, D. Generative AI: A Systematic Review Using Topic Modelling Techniques. Data Inf. Manag. 10. 2024, 8, 100066. [CrossRef]

11. Kshetri, N.; Dwivedi, Y.K.; Davenport, T.H.; Panteli, N.

Generative Artificial Intelligence in Marketing: Applications, Opportuni-ties, Challenges, and Research Agenda. Int. J. Inf. Manag. 2024, 75, 102716. [CrossRef]

12. Jin, Y.; Yan, L.; Echeverria, V.; Gaševi ́c, D.; Martinez-Maldonado, R.

Generative AI in Higher Education: A Global Perspective of Institutional Adoption Policies and Guidelines. Comput. Educ. Artif. Intell. 2025, 8, 100348. [CrossRef]

Zhang, P.; Kamel Boulos, M.N. Generative AI in Medicine and Healthcare: Promises, Opportunities and Challenges. Future 13. Internet 2023, 15, 286. [CrossRef] 14. Ooi, K.-B.; Tan, G.W.-H.; Al-Emran, M.; Al-Sharafi, M.A.; Capatina, A.; Chakraborty, A.; Dwivedi, Y.K.; Huang, T.-L.; Kar, A.K.; Lee, V.-H.; et al. The Potential of Generative Artificial Intelligence Across Disciplines: Perspectives and Future Directions. J. Comput. Inf. Syst. 2025, 65, 76–107. [CrossRef]

15. FAO.

AI Can Be a Game-Changing Solution for Farmers: FAO Innovation Chief. Available online: (accessed on 9 May 2025). 16. WIPO. Technology Based on Traditional Knowledge and Genetic Resources: Sharing the Benefits. Available online: the linked source (accessed on 21 April 2024).

17. Bawack, R.; Roderick, S.; Badhrus, A.; Dennehy, D.; Corbett, J.

Indigenous Knowledge and Information Technology for Sustainable Development. Inf. Technol. Dev. 2025, 31, 233–250. [CrossRef]

18. Chung, A.; Shedlock, K.; Corbett, J.

Decolonizing Information Technology Design: A Framework for Integrating Indigenous Knowledge in Design Science Research. In Proceedings of the Hawaii International Conference on System Sciences 2024 (HICSS-57), Honolulu, HI, USA, 3–6 January 2024.

19. Thomson, A.J.

Elicitation and Representation of Traditional Ecological Knowledge, for Use in Forest Management. Comput. Electron. Agric. 2000, 27, 155–165. [CrossRef]

Shahriar, S.; Corradini, M.G.; Sharif, S.; Moussa, M.; Dara, R. The Role of Generative Artificial Intelligence in Digital Agrifood. J. 20. Agric. Food Res. 2025, 20, 101787. [CrossRef]

21. Ruzzante, S.; Labarta, R.; Bilton, A.

Adoption of Agricultural Technology in the Developing World: A Meta-Analysis of the Empirical Literature. World Dev. 2021, 146, 105599. [CrossRef]

22. Mallinger, K.; Corpaci, L.; Neubauer, T.; Tikász, I.E.; Goldenits, G.; Banhazi, T.

Breaking the Barriers of Technology Adoption: Explainable AI for Requirement Analysis and Technology Design in Smart Farming. Smart Agric. Technol. 2024, 9, 100658. [CrossRef]

23. Fujisaka, S.

Learning from Six Reasons Why Farmers Do Not Adopt Innovations Intended to Improve Sustainability of Upland Agriculture. Agric. Syst. 1994, 46, 409–425. [CrossRef]

24. Douthwaite, B.; Keatinge, J.D.H.; Park, J.R.

Why Promising Technologies Fail: The Neglected Role of User Innovation during Adoption. Res. Policy 2001, 30, 819–836. [CrossRef] 25. Curry, G.N.; Nake, S.; Koczberski, G.; Oswald, M.; Rafflegeau, S.; Lummani, J.; Peter, E.; Nailina, R. Disruptive Innovation in Agriculture: Socio-Cultural Factors in Technology Adoption in the Developing World. J. Rural. Stud. 2021, 88, 422–431. [CrossRef] 26. Yigezu, Y.A.; Mugera, A.; El-Shater, T.; Aw-Hassan, A.; Piggin, C.; Haddad, A.; Khalil, Y.; Loss, S. Enhancing Adoption of Agricultural Technologies Requiring High Initial Investment among Smallholders. Technol. Forecast. Soc. Change 2018, 134, 199–206. [CrossRef]

FAO. Digital Agriculture in Action; FAO: Rome, Italy; ITU: Geneva, Switzerland, 2021; ISBN 978-92-5-135102-4. 27.

28. Timpanaro, G.; Foti, V.T.; Cascone, G.; Trovato, M.; Grasso, A.; Vindigni, G.

Living Lab for the Diffusion of Enabling Technologies in Agriculture: The Case of Sicily in the Mediterranean Context. Agriculture 2024, 14, 2347. [CrossRef]

Jha, S.K.; Singh, M.K.; van Nieuwkoop, M. UP PRAGATI Accelerator: A Model for Inclusive Innovation in the Intelligent Age. The 29. Water Blog. 2025. Available online: the linked source (accessed on 15 November 2024).

30. FAO.

FAO’s Elevate Programme. Available online: the linked source (accessed on 21 November 2024).

31. He, D.; Burdon, J.J.; Xie, L.; Zhan, J

Triple Bottom-Line Consideration of Sustainable Plant Disease Management: From Economic, Sociological and Ecological Perspectives. J. Integr. Agric. 2021, 20, 2581–2591. [CrossRef] 32. Kabbera, S.; Tibaingana, A.; Kiwala, Y.; Mugarura, J.T

Triple Bottom Line Practices and the Growth Agro-Processing Enterprises in Uganda. Clean. Circ. Bioeconomy 2024, 8, 100081. [CrossRef] 33. Luzzani, G.; Grandis, E.; Frey, M.; Capri, E

Blockchain Technology in Wine Chain for Collecting and Addressing Sustainable Performance: An Exploratory Study. Sustainability 2021, 13, 12898. [CrossRef] 34. Contreras-Medina, D.I.; Contreras-Medina, L.M.; Cerroblanco-Vázquez, V.; Gallardo-Aguilar, M.d.C.; González-Farías, J.P.; Medina-Cuellar, S.E.; Acosta-Montenegro, A.; Lemus-Martínez, L.Y.; Moreno-Ojeda, B.; Negrete-López, A.D. Reorienting Innovations for Sustainable Agriculture: A Study Based on Bean’s Traditional Knowledge Management. Agriculture 2025, 15, 560. [CrossRef] 35. Mariani, M.; Dwivedi, Y.K

Generative Artificial Intelligence in Innovation Management: A Preview of Future Research Develop-ments. J. Bus. Res. 2024, 175, 114542. [CrossRef] 36. Dwivedi, Y.K.; Kshetri, N.; Hughes, L.; Slade, E.L.; Jeyaraj, A.; Kar, A.K.; Baabdullah, A.M.; Koohang, A.; Raghavan, V.; Ahuja, M.; et al. Opinion Paper: “So What If ChatGPT Wrote It?” Multidisciplinary Perspectives on Opportunities, Challenges and Implications of Generative Conversational AI for Research, Practice and Policy. Int. J. Inf. Manag. 2023, 71, 102642. [CrossRef] 37. Google Modelos Grandes de Lenguaje Con La Tecnología de IA de Primer Nivel de Google. Available online: the linked source (accessed on 20 May 2025).

38. Taneja, A.; Nair, G.; Joshi, M.; Sharma, S.; Sharma, S.; Jambrak, A.R.; Roselló-Soto, E.; Barba, F.J.; Castagnini, J.M.; Leksawasdi, N.; et al. Artificial Intelligence: Implications for the Agrifood Sector. Agronomy 2023, 13, 1397. [CrossRef] 39. Suganthi, S.U.; Prinslin, L.; Selvi, R.; Prabha, R

Generative AI in Agri: Sustainability in Smart Precision Farming Yield Prediction Mapping System Based on GIS Using Deep Learning and GPS. Procedia Comput. Sci. 2025, 252, 365–380. [CrossRef] 40. Ogar, E.; Pecl, G.; Mustonen, T

Science Must Embrace Traditional and Indigenous Knowledge to Solve Our Biodiversity Crisis. One Earth 2020, 3, 162–165. [CrossRef] 41. World Bank Group

A Year in the Lives of Smallholder Farmers. Available online: (accessed on 14 April 2024).

Melash, A.A.; Bogale, A.A.; Migbaru, A.T.; Chakilu, G.G.; Percze, A.; Ábrahám, É.B.; Mengistu, D.K. Indigenous Agricultural 42. Knowledge: A Neglected Human Based Resource for Sustainable Crop Protection and Production. Heliyon 2023, 9, e12978. [CrossRef] [PubMed] 43. Kutyauripo, I.; Rushambwa, M.; Chiwazi, L

Artificial Intelligence Applications in the Agrifood Sectors. J. Agric. Food Res. 2023, 11, 100502. [CrossRef] 44. Mekonnen, Z.; Kidemu, M.; Abebe, H.; Semere, M.; Gebreyesus, M.; Worku, A.; Tesfaye, M.; Chernet, A. Traditional Knowledge and Institutions for Sustainable Climate Change Adaptation in Ethiopia. Curr. Res. Environ. Sustain. 2021, 3, 100080. [CrossRef] 45. Contreras-Medina, D.I.; Contreras-Medina, L.M.; Cerroblanco-Vázquez, V

Sustainable Agriculture Management: Environmental, Economic and Social Conjunctures for Coffee Sector in Guerrero, via Traditional Knowledge Management. Sustainability 2024, 16, 6864. [CrossRef] 46. Caldeira, M.; Sekinairai, A.T.; Vierros, M

Weaving Science and Traditional Knowledge: Toward Sustainable Solutions for Ocean Management. Mar. Policy 2025, 174, 106591. [CrossRef] 47. Ramírez-Terrazo, A.; Montoya, A.; Kong, A

Conocimiento Micológico Tradicional En Dos Comunidades Aledañas al Parque Nacional Lagunas de Montebello, Chiapas, México. Sci. Fungorum 2021, 51, e1321. [CrossRef]

Mejía-Trejo, J. Protection of Traditional Knowledge and Its Resulting Innovation. Sci. PRAXIS 2022, 1, 1–8. [CrossRef] 48.

49. Campos Saldaña, R.A.; Prado Lopez, M.; Martinez Camilo, R.; Salas Marina, M.A.; Rodriguez Larramendi, L.A. Use and Traditional Knowledge of Medicinal Plants in Communities of Villa Corzo, Chiapas, Mexico. Bol. Latinoam. Caribe Plantas Med. Aromat. 2024, 23, 257–272. [CrossRef] 50. García Flores, J.C.; Calvet-Mir, L.; Domínguez, P

Investigación Participativa Sobre El Conocimiento Ecológico Tradicional Asociado al Huerto Familiar En El Estado de México. Acta Univ. 2024, 34, 1–20. [CrossRef] 51. Reza-Solis, I.J.; Romero-Rosales, T.; Hernández Galeno, C.dÁ.; Valenzuela Lagarda, J.L.; Jiménez Lobato, V. Saberes Tradicionales En El Cultivo de Maíces Nativos. Rev. Biológico Agropecu. Tuxpan 2024, 12, 167–178. [CrossRef] 52. International Council for Science

Science-Traditional-Knowledge; International Council for Science: Paris, France, 2022.

53. INEGI

Diseño de La Muestra Proyectos de Encuesta; INEGI: Aguascalientes, Mexico, 2011.

54. Contreras-Medina, D.I.; Contreras-Medina, L.M.; Pardo-Nuñez, J.; Olvera-Vargas, L.A.; Rodriguez-Peralta, C.M. Roadmapping as a Driver for Knowledge Creation: A Proposal for Improving Sustainable Practices in the Coffee Supply Chain from Chiapas, Mexico, Using Emerging Technologies. Sustainability 2020, 12, 5817. [CrossRef] 55. INEGI Descarga Masiva

Available online: the linked source (accessed on 8 October 2023).

56. Mao, H.; Liu, S.; Zhang, J.; Deng, Z

Information Technology Resource, Knowledge Management Capability, and Competitive Advantage: The Moderating Role of Resource Commitment. Int. J. Inf. Manag. 2016, 36, 1062–1074. [CrossRef] 57. FAO

Bulding on Gender, Agrobiodiversity and Local Knowledge. Available online: (accessed on 17 March 2024).

Phaal, R.; Muller, G. An Architectural Framework for Roadmapping: Towards Visual Strategy. Technol. Forecast. Soc. Change 2009, 58. 76, 39–49. [CrossRef] 59. Ma, T.; Liu, S.; Nakamori, Y

Roadmapping as a Way of Knowledge Management for Supporting Scientific Research in Academia. Syst. Res. Behav. Sci. 2006, 23, 743–755. [CrossRef] 60. Mentzer, J.T.; DeWitt, W.; Keebler, J.S.; Min, S.; Nix, N.W.; Smith, C.D.; Zacharia, Z.G

Defining Supply Chain Management. J. Bus. Logist. 2001, 22, 1–25. [CrossRef] 61. FAO Science, Technology and Innovation

Available online: the linked source (accessed on 6 March 2025).

62. Toma, I.; Redman, M.; Czekaj, M.; Tyran, E.; Grivins, M.; Sumane, S

Small-Scale Farming and Food Security—Policy Perspectives from Central and Eastern Europe. Glob. Food Sec 2021, 29, 100504. [CrossRef] 63. Zhang, H.; Wu, C.; Xie, J.; Lyu, Y.; Cai, J.; Carroll, J.M

Harnessing the Power of AI in Qualitative Research: Exploring, Using and Redesigning ChatGPT. Comput. Human. Behav. Artif. Hum. 2025, 4, 100144. [CrossRef]

OECD. The Measurement of Scientific, Technological and Innovation Activities. In Oslo Manual 2018; OECD: Paris, France, 2018; 64. ISBN 9789264304550.

65. Contreras-Medina, D.I.; Sánchez Osorio, E.; Olvera Vargas, L.A.; Romero Romero, Y

Technology Roadmapping Architecture Based on Knowledge Management: Case Study for Improved Indigenous Coffee Production from Guerrero, Mexico. J. Sens. 2019, 2019, 1–17. [CrossRef] 66. Wang, T.; Wang, Z.; Guo, L.; Zhang, J.; Li, W.; He, H.; Zong, R.; Wang, D.; Jia, Z.; Wen, Y. Experiences and Challenges of Agricultural Development in an Artificial Oasis: A Review. Agric. Syst. 2021, 193, 103220. [CrossRef] 67. FAO

Tecnologías Digitales en la Agricultura y las Zonas Rurales; FAO: Roma, Italy, 2019.

68. Martinez, L.; Soti, P.; Kaur, J.; Racelis, A.; Kariyat, R.R

Impact of Cover Crops on Insect Community Dynamics in Organic Farming. Agriculture 2020, 10, 209. [CrossRef] 69. Choruma, D.J.; Dirwai, T.L.; Mutenje, M.J.; Mustafa, M.; Chimonyo, V.G.P.; Jacobs-Mata, I.; Mabhaudhi, T. Digitalisation in Agriculture: A Scoping Review of Technologies in Practice, Challenges, and Opportunities for Smallholder Farmers in Sub-Saharan Africa. J. Agric. Food Res. 2024, 18, 101286. [CrossRef] 70. Kamara, A.Y.; Kamsang, L.S.; Mustapha, A.; Kamara, A.Y.; Kolapo, A.; Kamai, N

Gender Disparities in the Adoption of Improved Management Practices for Soybean Cultivation in North East Nigeria. J. Agric. Food Res. 2025, 22, 102032. [CrossRef] [PubMed]

Hruska, A. Agricultura Familiar y Acceso a los Mercados. Memoria del Seminario-Taller Realizado por la Oficina Sub-Regional de FAO 71. Para Mesoamérica Coordinación de La Publicación; FAO: Rome, Italy, 2013; ISBN 9789253079469.

72. Ocama, O.V.; Medagbe, Y.-C.N.; Akello, S.; Kambale, W.V.; Tashev, T.; Kyamakya, K.; Kasereka, S.K

A Review on Advancing Technologies in Precision Agriculture: Applications, Challenges, and the Way Forward. Procedia Comput. Sci. 2025, 265, 572–577. [CrossRef] 73. Padhiary, M.; Saha, D.; Kumar, R.; Sethi, L.N.; Kumar, A

Enhancing Precision Agriculture: A Comprehensive Review of Machine Learning and AI Vision Applications in All-Terrain Vehicle for Farm Automation. Smart Agric. Technol. 2024, 8, 100483. [CrossRef] 74. Kumar, V.; Sharma, K.V.; Kedam, N.; Patel, A.; Kate, T.R.; Rathnayake, U

A Comprehensive Review on Smart and Sustainable Agriculture Using IoT Technologies. Smart Agric. Technol. 2024, 8, 100487. [CrossRef] 75. Andersen, J.P.; Degn, L.; Fishberg, R.; Graversen, E.K.; Horbach, S.P.J.M.; Schmidt, E.K.; Schneider, J.W.; Sørensen, M.P. Generative Artificial Intelligence (GenAI) in the Research Process—A Survey of Researchers’ Practices and Perceptions. Technol. Soc. 2025, 81, 102813. [CrossRef] 76. FAO

Estructura y Financiación. Available online: the linked source descentralizada%20de%20la,cubiertos%20a%20trav%C3%A9s%20de%20la (accessed on 12 November 2025).

Disclaimer/Publisher’s Note: The statements, opinions and data contained in all publications are solely those of the individual author(s) and contributor(s) and not of MDPI and/or the editor(s). MDPI and/or the editor(s) disclaim responsibility for any injury to people or property resulting from any ideas, methods, instructions or products referred to in the content.