Rice cultivation is the main economic livelihood for many families around the world. This activity represents several challenges for farmers and community members for rural sustainability, a cross-cutting element of the Sustainable Development Goals (SDGs) of the United Nations (UN). In response, the Polytechnic University (ESPOL), fulfilling its mission of linking with society, implemented a community program where students and professors interact and collaborate with rice farmers in the rural community of Paipayales, located in the Santa Lucia canton, Guayas province. This article explores the impact of university-community projects through the Participatory Action Research (PAR) approach in order to evaluate them as a tool for contributing towards rural sustainability in communities. As a result, it was determined that the main problems faced by most of the farmers of the “Dios con Nosotros” Association are the availability of water in the wells and the commercialization of paddy rice. Considering these problems, the wells were geolocated and a board was designed for proper water management; at the same time, water quality was studied and recommendations were presented according to the problems encountered. Two proposals were also presented to create a rice husker and a rice separator to increase their profit margin by selling rice directly to retailers and wholesalers. As relevant conclusions, the importance of implementing links and relationships between the university community and society was highlighted, guaranteeing the value of working in transdisciplinary teams and achieving a comprehensive intervention that would lead to significant improvements in the community.

The present study was focused on organic small tea plantations of Sittong (a village in Darjeeling) mainly due to their sudden rise in the Indian tea industry with a striking tactic i.e., organic tea cultivation. This cumulative survey and laboratorial experiments-based research focuses on the agricultural conversion in Sittong where farmers started to shift from vegetable and grain cultivation to small tea gardens. Soil physicochemical (pH and electric conductivity; organic carbon; organic matter; and available nitrogen content) and microbiological (determination of microbial cell mass and isolation of consortia; antibiotic and antifungal susceptibility test) characteristics were considered to assess the viability of this shifting agriculture practice and cross-verify the reflections of organic farming practices. The survey revealed that farmers have cultivated and rehabilitated the land in an acceptable manner before planting; they carried out the soil nutrient management practices organically. Survey also revealed economic perspectives including prices of their harvested tea leaves. Further, the moisture content analysis revealed its adequacy in the tea garden soils. Organic matter, organic carbon and available nitrogen were measured that reflected very high results compared to the optimum values suggested by the Tea Board of India. Microbial analysis results, as a cross-verifying tool, affirmed their organic farming practice by revealing microbes’ susceptible nature towards antibiotics and antifungals. Overall, the findings of this study suggest that the small tea growers in Sittong-3 are well-positioned to produce a high-quality of organic tea. Sittong was found to have potential to promote the rural areas of Darjeeling into an ideal place for small-scale organic tea cultivation, while also serving as an inspiration for small tea growers across the country.

Global overpopulation necessitates increased crop yields, yet available arable land is limited. The study compares and evaluates the performance of three machine learning algorithms—Random Forest (RF), Extra Trees (ET), and Artificial Neural Network (ANN)—in crop yield prediction. Using 28,242 samples with seven features from 101 countries, we evaluated these models based on Mean Absolute Error (MAE), R-squared (R^2), and Mean Squared Error (MSE). The ET regression model demonstrated superior performance, achieving an MAE of 5249.03, the lowest among the models tested. Despite having the highest R^2 value of 0.9873, the ANN exhibited higher MAE and MSE values, indicating less reliability. The RF model showed intermediate results. With a prediction accuracy of 97.5%, the ET model proved to be the most effective for crop yield prediction, achieving the highest accuracy reported to date. Future research should explore more advanced algorithms and larger datasets to validate these findings further.