With rising climate volatility threatening agricultural sustainability, Climate-Smart Agriculture (CSA) has emerged as a critical strategy to ensure food security. While CSA practices are proven effective, their large-scale implementation is often hindered by fragmented data and limited decision-support tools. This study introduces a novel machine learning-driven framework, originally developed for subsurface reservoir characterization in the petroleum sector, and adapts it for enhancing CSA adoption, productivity, and resource-use efficiency.

Using geospatial, soil, and weather data from diverse agro-climatic zones, we implemented zonation-based predictive modeling to classify land into CSA suitability regions. A suite of ML algorithms—Random Forest, Gradient Boosting, and spatial interpolation models—was applied to estimate moisture stress, optimize irrigation zones, and predict crop-specific productivity under varying climate scenarios. The model was trained on multi-source data and validated using ground truths from 320 smallholder farms. Additionally, stochastic frontier analysis (SFA) was used to assess the efficiency impacts of CSA interventions.

The ML-adapted framework enabled high-resolution mapping of optimal CSA practices, achieving over 85% accuracy in zone classification and a 20% gain in predictive precision compared to baseline methods. Farms implementing model-guided CSA strategies showed a 23% improvement in productivity and a 17% increase in technical efficiency. The system also proved valuable in identifying vulnerable zones to climate shocks, aiding in targeted intervention planning.

This work demonstrates the cross-domain applicability of AI/ML models from petroleum engineering to climate-smart agriculture. By translating subsurface zonation logic to surface-level agroecological analysis, we offer a scalable, data-driven solution for accelerating CSA adoption. Future directions include integrating real-time satellite feeds and farmer feedback loops to evolve the framework into a dynamic advisory tool for climate-resilient farming.

Precision irrigation is a novel concept that optimizes water use precisely when and where needed, thereby enhancing crop productivity and water use efficiency. It involves accurate monitoring of crop and soil parameters to determine the appropriate amount of water for healthy plant growth and crop production. The present study highlights the usage of precision irrigation across vegetable fields practicing monoculture farming in the Baruipur, Sonarpur, and Jaynagar blocks of South 24-Parganas district, West Bengal, India, from April 2024 to March 2025. Cultivation of Trichosanthes dioica, Abelmoschus esculentus, Cucurbita maxima, Cucumis sativus, Luffa acutangula, and Trichosanthes cucumerina was practiced. This study involves an array of sensors (soil, moisture, temperature, humidity, crop growth monitoring, and soil nutrient analyzer), algorithms, and drip tip and sprinkler irrigation for formulating an optimum irrigating schedule. K-nearest neighbors, logistic regression, support vector machine, decision tree, random forest, and the gradient boosting algorithm were used for analysis using the Raspberry Pi microprocessor. A watering schedule was designed based on the signal generated by a microcontroller. Sprinkler irrigation at 50% Depletion of Available Soil moisture (DASM) was employed for the studied cropping system. Thus, in a typical crop production system, water productivity (WP) was defined as the relationship between crops produced and the amount of water provided for the said purpose. WP in the crop field under the traditional watering schedule recorded values between 18.22 kg/ha/cm^. (Cucurbita maxima) and 48.65 kg/ha/cm (Trichosanthes dioica). However, utilizing precision irrigation techniques yielded results varying between 22.15kg/ha/cm (Trichosanthes cucumerina) and 52.68 kg/ha/cm (Cucumis sativus). The Random Boost algorithm (accuracy=98.20% for Cucurbita maxima), random forest (accuracy=97.5 % for Trichosanthes cucumerina), and decision tree (accuracy=97.20% for Trichosanthes cucumerina) were found to provide the most accurate results. In spite of the prevalence of small, illiterate landholders, adoption of such digitized technologies appears quite rewarding for the farming community.

Environmentally sustainable agriculture is increasingly based on an approach that addresses the overlapping issues of climate change, food security, increasing sustainable agricultural productivity, maintaining healthy soils, and reducing greenhouse gas emissions. It is essential to look for innovative ideas that can help address these issues. One solution could be the application of a range of innovative agricultural practices, such as the use of autonomous and robotic machinery in agricultural processes. The aim of this work was to analyse trends in the use of autonomous robots in crop production from an environmental perspective. A comprehensive analysis of literature sources in the databases ScienceDirect, Web of Science, and Google Scholar was carried out. A carefully selected set of keywords was used to find articles relevant to this work, including “autonomous agricultural machines”, “agricultural robotics”, “sowing robots”, “weed control robots”, “tillage robots”, “harvesting robots”, and other related secondary keywords. The search for information focused only on the crop sector without touching on livestock, logistics, horticulture, and gardening. Autonomous agricultural machines used in crop production have been classified according to work processes: tillage, sowing, spraying and fertilising, weed control, and harvesting. A diagram of the environmental impact of autonomous machines in agriculture has been drawn up, which shows that autonomous agricultural machines have a positive impact on the physical and chemical properties of the soil, on the optimisation of resources, and on the production of higher yields. The efficiency of an autonomous system is between 3.0 and 9.6 % better than tat of a conventional machine, and the difference in CO2 emissions between autonomous and conventional systems shows that an automated system is able to emit between 11.0 and 63.3% less CO2 into the environment. In addition, in many cases, a robotic system is several times lighter than a conventional system and has a lower impact on soil structure than conventional earth-moving machinery. Autonomous machines are poised to have a significant impact on the development of crop production in terms of environmental sustainability. The integration of these intelligent technological solutions into agriculture is in line with the principles of climate-friendly agriculture, increasing the efficiency and sustainability of farming practices. Autonomous equipment, such as solar-powered robotic systems, can carry out technological processes with the least possible disturbance to the environment, while optimising the use of resources and thus reducing the negative environmental impacts associated with traditional farming methods.

Two important abiotic factors that significantly reduce crop productivity in arid and semi-arid settings are salinity and water scarcity. Optimizing crop productivity in saline and water-limited environments has become a critical global concern due to the acceleration of climate change and the depletion of freshwater supplies. In order to maintain crop performance in these demanding conditions, this paper examines current developments in soil–water techniques, crop physiology, and irrigation management. Complex physiological responses, such as osmotic adjustment, changes in root architecture, and activation of the antioxidant defense, are displayed by plants subjected to combined salt and drought stress. These characteristics are essential for sustaining output under pressure. At the same time, it has been demonstrated that cutting-edge irrigation techniques, including alternate furrow irrigation, partial root-zone drying (PRD), and regulated deficit irrigation (RDI), improve water consumption efficiency while lowering salt accumulation in the root zone. Crop resilience is further enhanced by the use of salt-tolerant cultivars, soil additives (such as compost and gypsum), and advantageous microorganisms like plant growth-promoting rhizobacteria (PGPR). Precise crop and soil status monitoring is made possible by remote sensing and decision-support tools, which lower risks and maximize input efficiency. This study emphasizes the need for a comprehensive, site-specific strategy that incorporates agroecological techniques, intelligent irrigation, and physiological knowledge. In order to optimize yield in saline and drought-prone environments, interdisciplinary cooperation and locally relevant solutions that are adapted to particular soil, climatic, and socioeconomic circumstances are essential. In conclusion, the study provides a thorough framework for enhancing yield under combined salinity and water stress using coordinated, scientifically supported tactics. The advancement of climate-resilient agriculture and the direction of upcoming studies, regulations, and field-level operations in marginal settings depend heavily on these findings.

Bangladesh faces severe environmental risks from untreated tannery wastewater containing toxic hexavalent chromium (Cr VI), which harms plant growth. Microorganisms that convert Cr (VI) to less toxic Cr (III) offer a potential detoxification solution. The present study aimed to evaluate the effects of Cr stress on soybean (Glycine max L.) under different Cr concentrations (0, 50, and 100 mg/kg) added from Cr salt and tannery wastewater (TW44 and TW88 mg/kg) and evaluate the efficacy of a Cr (VI)-reducing bacterial strain, Tan3, in reducing stress on the plant. Increasing Cr concentrations clearly lowered plant height, biomass, chlorophyll content, and yield attributes. TW88-treated plants showed the greatest decline in chlorophyll b by 34.5%, total chlorophyll (15.88%), carotenoid content by 64.1%, shoot fresh (13.94%), and dry biomass (25.52%) and also the lowest number of pods. Chromium stress also triggered oxidative stress responses, an increase in MDA levels (from 26.17 to 57.36 nmol/g FW), proline content, H₂O₂, and superoxide under 100 mg/kg Cr. Tan3 inoculation significantly alleviated these effects by reducing their activities. Tan3 bacterial inoculation also markedly alleviated Cr-induced stress across all treatments by reducing oxidative damage, enhancing antioxidant enzyme activity (CAT, POD, GST, APX, GPX), improving nutrient uptake (N, P, S, Mg), and decreasing Cr accumulation in plant tissue. Cr accumulation in plant tissues was highest in soil (165.08 mg/kg) and in tannery wastewater (88 mg/kg). In post-harvest soil, Cr concentration was higher in Tan3-inoculated soil than in respective uninoculated soil, suggesting bacterial immobilization of Cr in soil that ultimately reduced the phytoavailability and translocation of Cr from soil to root, shoot, and pod. These findings clearly show that the complex mixture of contaminants causes TW88 to have the greatest negative consequences, but Tan3 inoculation can efficiently minimize Cr-induced damage by means of physiological protection, oxidative stress reduction through antioxidative enzymes, and lower Cr absorption in plants.

Climate-smart agriculture provides a transformative paradigm for sustainable development and food security. While CSA emphasizes increased productivity and enhanced resilience, its successful implementation is fundamentally contingent on inclusive participation. In Morocco, rural women are central to labor and agricultural systems. However, they often face significant barriers and remain disproportionately marginalized from engaging fully in sustainable practices. Accordingly, this research critically examines the role of rural women’s empowerment in contributing to sustainable agricultural practices in Morocco’s Fez-Meknes region.

This paper employed a mixed-methods approach. We conducted semi-structured interviews with key stakeholders, including government officials, community representatives, and non-governmental organizations. In the next step, we administered questionnaires to female-led cooperatives and farmers. The data analysis provided us with a contextual understanding of stakeholders’ perspectives on the existing policies. It allowed us to perform a thorough assessment of women’s involvement in sustainable agricultural practices. Moreover, we identified a set of barriers impeding their full participation in the adoption of such practices.

Our results indicate limited participation of rural women in the adoption of innovative CSA practices in the Fez-Meknes region. Despite their significant contribution to agricultural labor, they face numerous restrictions in terms of access to financial resources, education, and information networks. Notwithstanding, our research highlights a substantive correlation between inclusive policies and increased adoption of sustainable agricultural practices. Furthermore, female-led cooperatives demonstrated enhanced collective action, leading to knowledge sharing and more effective results.

This research explores the role rural women play in adopting sustainable agricultural practices. It confirms that conceiving and implementing inclusive policies leads to the empowerment of women through education, training, and resource provision. Enhancing women’s participation in CSA initiatives is thus a prerequisite for achieving robust and sustainable agricultural development in Morocco.

Introduction:
Water management in agriculture is a critical factor in national development. Although the Earth's water reserves are sufficient, uneven distribution—worsened by climate change and conflicts—limits agricultural productivity in many underdeveloped countries. Ensuring equitable access and sovereign rights to water is both a developmental priority and a matter of sovereignty. In today’s AI-driven era, agricultural water management is a key driver of economic development and sustainability.

Methods:
This study will use customized AI models trained on historical and recent data from water resource authorities and surveys. Economic models linking water management to financial stability will be integrated into these algorithms. Extensive surveys and field interviews will collect data on local water challenges and community practices. This mixed-method approach aims to develop adaptable, sustainable water management solutions for underdeveloped regions.

Expected Results:
Implementation of the proposed system is expected to reduce water wastage by up to 40% and increase crop yields by 25–35%. Improved water governance will enhance the economic conditions of farming communities, stabilizing livelihoods and enabling better household investment in education. These social improvements may lead to healthier populations and more informed citizens, contributing to national GDP and GNI growth.

Conclusions:
This research demonstrates that intelligent design and participatory management of agricultural water can drive economic transformation in underdeveloped nations. Harnessing AI and civil engineering innovations can accelerate sustainable development, making agricultural water management a cornerstone of future economic progress.

Rice is a staple food for many Asian countries; however, identifying climate-smart rice management practices has become increasingly important to fighting climate change. This study comprehensively evaluated the agronomic, environmental, and economic performance of various rice production techniques over two winter seasons (2020 and 2021), with a focus on sustainability and climate-smart agriculture. The evaluated methods included System of Rice Intensification with Alternate Wetting and Drying (SRI-AWD), Direct Seeded Rice with AWD (DSR-AWD), and Traditional Farmers’ Practices under Continuous Flooding (FPR-CF). Among these, SRI-AWD significantly outperformed the others, achieving up to 39.4% higher grain yield, enhanced straw yield, harvest index, and water productivity, while reducing total water use by 37.5%. DSR-AWD recorded the lowest energy inputs, and both SRI-AWD and DSR-AWD demonstrated the highest energy use efficiency. Greenhouse gas emissions—particularly methane—were substantially reduced under AWD-based systems, with SRI-AWD exhibiting the lowest global warming potential. Soil health indicators, including labile carbon fractions, microbial populations, and enzyme activities, were markedly improved under SRI-AWD, correlating positively with increased soil organic carbon and microbial activity. Regression analysis identified soil water-soluble carbon and bacterial populations as key determinants of yield, while methanogens and denitrifiers were the main drivers of greenhouse gas emissions. Economically, SRI-AWD yielded the highest gross and net returns (34.9% and 122% higher, respectively), along with the most favorable benefit–cost ratio and climate-smart index (CSI), reflecting higher productivity, climate resilience, and a more efficient use of resources. In contrast, FPR-CF proved to be the least sustainable option. Overall, SRI-AWD emerged as the most sustainable, profitable, and climate-smart rice cultivation strategy, offering a viable pathway toward resilient and eco-efficient rice production systems.

With a specific focus on reduced tillage and organic fertilization, this study examines the effects of conservation agriculture practices on soil greenhouse gas (GHGs—CO₂, N₂O, and CH₄) emissions, global warming potential (GWP), maize productivity, and greenhouse gas intensity (GHGI) over two growing seasons (2020 minor and 2021 main season) in Buea, Cameroon. Two tillage practices, i.e., zero-tillage and conventional tillage, and three fertilizer treatments, i.e., no fertilizer, synthetic fertilizer (urea), and organic fertilizer (composted municipal solid waste), were factorially combined in a split-plot design with three replications. The hybrid maize cultivar CMS 8704 was used. GHG emissions were measured using the static flux chamber method, and flux rates were calculated with the HMR package in R software. The results showed that tillage and fertilizer types significantly (p<0.05) influenced seasonal cumulative CO₂, N₂O, and CH₄ emissions. Synthetic fertilizer treatments produced the highest cumulative N₂O emissions, particularly under zero-tillage in 2020 and conventional tillage in 2021. Conventional tillage paired with organic fertilizer yielded the highest CO₂ emissions across both seasons, while methane fluxes were low and largely negative across treatments, indicating that the volcanic upland soils acted as CH₄ sinks. Application of synthetic fertilizer increased GWP by 20% and 322% under no-tillage in the 2020 and 2021 seasons, respectively. Under conventional tillage, GWP decreased by 15% in 2020 but sharply increased by 295% in 2021, highlighting season-specific effects. Although treatment effects were not significant (P>0.05) on maize yields in 2020, the highest yield (3.06 t/ha) occurred under conventional tillage without fertilization. Fertilizer type and its interaction with tillage significantly (P<0.05) influenced yields in 2021, with the highest yield under conventional tillage with synthetic fertilization (6.15 tons/ha). However, conventional tillage treatment without fertilization produced the highest yield (3.06 t/ha) in 2020 and the lowest GHGI (12.04 kg CO₂-eq t⁻¹). In 2021, zero tillage treatment without fertilization resulted in a high yield (5.56 t/ha) with the lowest GHGI (2.15 kg CO₂-eq t⁻¹). The results suggest that in Buea’s minor growing season, conventional tillage with or without organic fertilization reduced GHG emissions without compromising yields, while in main seasons, zero tillage without fertilization offered the most favorable yield-emission balance. This study highlights the importance of context-specific soil and nutrient management strategies for sustainable agriculture and climate change mitigation. The findings provide valuable data for national GHG inventory reporting and inform conservation agriculture practices in tropical upland agricultural systems.

Sangamner block in Ahmednagar district, Maharashtra, India, is a semi-arid region receiving only 500 – 750 mm of annual rainfall. Heavy reliance on agriculture, coupled with steadily declining groundwater levels, heightens farmers’ climate vulnerability. Drip irrigation, a climate-resilient technology, is increasingly adopted in response.

This study employed a cross-sectional survey conducted in July 2024, covering 159 farming households from six villages (Kawthe Malkapur, Kolwade, Kumbharwadi, Pimpalgaon Depa, Shendewadi, and Warwandi). Structured interviews captured data for the 2023–2024 agricultural year, including household demographics, institutional support, government-scheme access, and crop production.

Binary logistic regression identified education, social group, FPO membership, land size, and age as significant predictors. Farmers with low and medium education levels are 84% (OR = 0.16, p = 0.017) and 74% (OR = 0.26, p = 0.035) less likely to adopt drip irrigation compared to highly educated farmers. Social group-wise, Other Backward Class (OBC) farmers are four times more likely to adopt drip irrigation than Scheduled Tribe farmers (OR = 4.037, p = 0.004). Each additional acre of land and each extra year in age raised adoption odds by 14.5% (p = 0.015) and 4% (p = 0.046), respectively. Lastly, Farmer Producer Organisation (FPO) membership was the strongest driver, with non-members being 87% less likely to adopt drip irrigation (OR = 0.126, p < 0.001). Conversely, gender and government schemes, including Kisan Credit Cards, Soil Health Cards, and Pradhan Mantri Fasal Bima Yojana, showed no significant relationship.

Descriptive analysis revealed that traditional climate-resilient cereals (bajra, jowar) achieved stable yields across all irrigation types, whereas high-value, water-sensitive crops like onion and tomato yielded 8 to 50 times higher yields under drip systems.

These findings highlight the need for targeted educational interventions and FPO-based extension programs to accelerate drip adoption, particularly focusing on marginalized communities and less-educated farmers to strengthen climate resilience in water-stressed regions.