While several studies have focused on the actual adoption of agricultural apps and the relevance of the apps’ content, very few studies have focused on drivers of the farmer’s intention and initial decision to adopt. Based on a survey of 394 smallholder farmers in 2019, this study investigated willingness to adopt an agricultural advice app in Guanajuato, Mexico. A structural equation modeling approach, based on the unified theory of acceptance and use of technology (UTAUT), was applied. To understand the farmers’ adoption decisions, extended constructs were studied (e.g., mastery-approach goals) along with the farmers’ age and participation in an innovation hub. Results showed that the intention to adopt the app is predicted by how farmers appraise the technical infrastructure and acquire new knowledge by using an app. The multi-group analysis revealed that performance expectancy is a relevant predictor of the intention to adopt, whereas the mastery-approach goal is relevant only for younger farmers and farmers not connected to the innovation hub. This study provides valuable insights about the innovation hubs’ role in the intention to adopt apps, offering precision agriculture advice in developing countries. The findings are useful for practitioners and app developers designing digital-decision support tools.

Traditional agricultural extension services rely on extension workers, especially in countries with large agricultural areas. In order to increase adoption of sustainable agriculture, the recommendations given by such services must be adapted to local conditions and be provided in a timely manner. The AgroTutor mobile application was built to provide highly specific and timely agricultural recommendations to farmers across Mexico and complement the work of extension agents. At the same time, AgroTutor provides direct contributions to the United Nations Sustainable Development Goals, either by advancing their implementation or providing local data systems to measure and monitor specific indicators such as the proportion of agricultural area under productive and sustainable agriculture. The application is freely available and allows farmers to geo-locate and register plots and the crops grown there, using the phone’s built-in GPS, or alternatively, on top of very high-resolution imagery. Once a crop and some basic data such as planting date and cultivar type have been registered, the application provides targeted information such as weather, potential and historical yield, financial benchmarking information, data-driven recommendations, and commodity price forecasts. Farmers are also encouraged to contribute in-situ information, e.g., soils, management, and yield data. The information can then be used by crop models, which, in turn, send tailored results back to the farmers. Initial feedback from farmers and extension agents has already improved some of the application’s characteristics. More enhancements are planned for inclusion in the future to increase the application’s function as a decision support tool.

Mobile phone apps can be a cost-effective way to provide decision support to farmers, and they can support the collection of agricultural data. The digitisation of agricultural systems, and the efforts to close the digital divide and to include smallholders, make data ownership and privacy issues more relevant than ever before. In Central and South American countries, smallholders’ preferences regarding data licenses and sharing have largely been ignored, and little attention has been paid to the potential of nonfinancial incentives to increase the uptake of digital solutions and participation by farmers. To investigate incentives for smallholder farmers to potentially use an agricultural advisory app in which they share their data, a Discrete Choice Experiment was designed. Based on a survey of 392 farmers in Mexico, preferences for attributes related to its usage were revealed using a conditional logit (CL) model. To explore heterogeneity, groups and profiles were explored through a latent class (LC) model. The CL model results revealed, for example, farmers’ positive preference to receive support at first use and access to training, while negative preference was found for sharing data with private actors. The LC identified three classes which differ in their preference for attributes such as the degree of data sharing. Furthermore, for example, a farmer’s connectedness to an innovation hub was found to be one of the significant variables in the class membership function. The main contribution of the study is that it shows the importance of nonfinancial incentives and the influence of data sharing on farmer preferences.

For several decades, maize (Zea mays L.) management decisions in smallholder farming in tropical regions have been a puzzle. To best balance alternative management practices' environmental and economic outcomes, an extensive dataset was gathered through CIMMYT's knowledge hub in Chiapas, a state in southern Mexico. In a knowledge hub, farmers, with the support of farm advisors, compare conventional and improved agronomic practices side-by-side and install demonstration fields where they implement improved practices. In all these fields data on on-farm operations and results is collected. The dataset was assembled using field variables (yield, cultivars, fertilization and tillage practice), as well as environment variables from soil mapping (slope, elevation, soil texture, pH and organic matter concentration) and gridded weather datasets (precipitation, temperature, radiation and evapotranspiration). The dataset contains observations from 4585 fields and comprises a period of 7 years between 2012 and 2018. This dataset will facilitate analytical approaches to represent spatial and temporal variability of alternative crop management decisions based on observational data and explain model-generated predictions for maize in Chiapas, Mexico. In addition, this data can serve as an example for similar efforts in Big Data in Agriculture.

This data descriptor presents a decade-long agronomic dataset collected between 2012 and 2022 by extension agents across Mexico as part of CIMMYT’s on-farm experimentation network. Extension agents used a unified digital logbook platform (BEM, later e-Agrology) to record agronomic activities, farm operations, and results. After multi-stage cleaning and validation, the dataset comprises 69,008 logbooks from 10,763 innovation plots testing new technologies, 10,305 control plots under conventional management, and 47,940 extension plots adopting sustainable practices. Key variables cover crop management (including sowing and harvest dates), resource use (including inputs, fuel and labor), activity costs, market prices, and yields for maize (Zea mays), beans (Phaseolus vulgaris), wheat (Triticum aestivum, Triticum durum), sorghum (Sorghum bicolor), and barley (Hordeum vulgare). Spanning diverse agroecologies and farm sizes, this open-access resource enables analyses of long-term productivity trends, cost–benefit relationships, input–output efficiencies, and climate-related performance. By providing harmonized, field-level data across multiple management scenarios, it can be used to derive valuable insights for researchers, extension services, and policymakers to develop optimized agronomic recommendations and sustainable intensification strategies.