The soil–environmental relationship identified and standardised over the years has expedited the growth of digital soil-mapping techniques; hence, various machine learning algorithms are involved in predicting soil attributes. Therefore, comparing the different machine learning algorithms is essential to provide insights into the performance of the different algorithms in predicting soil information for Indian landscapes. In this study, we compared a suite of six machine learning algorithms to predict quantitative (Cubist, decision tree, k-NN, multiple linear regression, random forest, support vector regression) and qualitative (C5.0, k-NN, multinomial logistic regression, naïve Bayes, random forest, support vector machine) soil information separately at a regional level. The soil information, including the quantitative (pH, OC, and CEC) and qualitative (order, suborder, and great group) attributes, were extracted from the legacy soil maps using stratified random sampling procedures. A total of 4479 soil observations sampled were non-spatially partitioned and intersected with 39 environmental covariate parameters. The predicted maps depicted the complex soil–environmental relationships for the study area at a 30 m spatial resolution. The comparison was facilitated based on the evaluation metrics derived from the test datasets and visual interpretations of the predicted maps. Permutation feature importance analysis was utilised as the model-agnostic interpretation tool to determine the contribution of the covariate parameters to the model’s calibration. The R² values for the pH, OC, and CEC ranged from 0.19 to 0.38; 0.04 to 0.13; and 0.14 to 0.40, whereas the RMSE values ranged from 0.75 to 0.86; 0.25 to 0.26; and 8.84 to 10.49, respectively. Irrespective of the algorithms, the overall accuracy percentages for the soil order, suborder, and great group class ranged from 31 to 67; 26 to 65; and 27 to 65, respectively. The tree-based ensemble random forest and rule-based tree models’ (Cubist and C5.0) algorithms efficiently predicted the soil properties spatially. However, the efficiency of the other models can be substantially increased by advocating additional parameterisation measures. The range and scale of the quantitative soil attributes, in addition to the sampling frequency and design, greatly influenced the model’s output. The comprehensive comparison of the algorithms can be utilised to support model selection and mapping at a varied scale. The derived digital soil maps will help farmers and policy makers to adopt precision information for making decisions at the farm level leading to productivity enhancements through the optimal use of nutrients and the sustainability of the agricultural ecosystem, ensuring food security.

Rice is a staple food for billions of people worldwide, yet its production is increasingly threatened by the impacts of climate change. Rising temperatures, irregular precipitation patterns, increased salt and increasing frequency of extreme weather events significantly compromise both rice yield and grain quality. Key stressors such as heat induced spikelet sterility, drought-induced reduction in tillering and grainfilling, salt stress inhibiting plant growth and flooding during critical growth stages pose serious challenges to productivity. Moreover, altered climatic conditions promote pest and disease outbreaks, exacerbate soil degradation, accelerate nitrogen loss and lead to salinity build-up further diminishing agricultural output. Smallholder farmers face socioeconomic vulnerability due to limited resources, inadequate technological access and insufficient adaptive capacity. Enhancing resilience involves innovations like establishing climate-resilient rice cultivars using sophisticated breeding procedures to improve tolerance to heat, drought, flooding and salinity challenges. Precision agriculture technologies (remote sensing, drones) optimize inputs through datadriven decisions. Sustainable approaches including alternate wetting/drying, direct-seeded rice and the System of Rice Intensification, conserve water. Climate-smart farming incorporating conservation agriculture, integrated crop-livestock systems and agroforestry increases overall resilience. Facilitating smallholders' access to climate information services, finance, insurance and capacity building is vital for boosting adaptive capacity. A coordinated, multi-pronged approach incorporating research, technical solutions, policy assistance and community engagement is necessary to create resilient rice farming systems capable of withstanding climate change impacts while maintaining food security.

Remote Sensing (RS) technology, which harnesses electromagnetic radiation, has changed agricultural disaster management. By identifying spectral signatures generated various objects on the Earth's surface, it enables effective monitoring of crop health, soil conditions and environmental changes. RS linked with Geographic Information Systems (GIS), prioritizes response actions, anticipates damaged areas and simulates disaster scenarios, revolutionizing disaster management approaches. Integration with modern analytics, such as machine learning, enhances catastrophe impact assessments, agricultural production estimations and land cover classification, thereby boosting disaster preparedness and response. Recent innovations, such as Unmanned Aerial Vehicles (UAVs) and high-resolution satellite imaging systems, offer rapid mapping of flooded areas and accurate post-disaster damage assessment. The merging of remote sensing with artificial intelligence (AI) and big data analytics further enhances disaster response and management, lowering the dangers associated with socio-ecological vulnerability. However, obstacles remain, including the need to boost sensor capabilities, improve data delivery and address regulatory issues with UAVs. Future directions include combining hazard and disaster process models, developing user-centric solutions and utilizing IoT and big data for more accurate disaster prediction and mitigation. Overall, RS and GIS offer vital tools for mitigating agricultural disasters, delivering early information for decision-making and decreasing the impact on food security and agricultural output.

The rapid growth of agro-industrial activities has led to the generation of substantial quantities of effluent sludge, posing serious environmental and waste management concerns. Despite these challenges, agro-industrial sludge contains significant amounts of organic matter and plant nutrients, making it a valuable resource for agricultural applications when properly treated. This review explores the conversion of agro-industrial effluent sludge into biofertilisers as a sustainable strategy for waste valorisation and nutrient recycling within a circular bioeconomy framework. It discusses the characteristics of sludge, associated environmental risks and the treatment processes required to ensure safe agricultural use. Major bioconversion approaches, including composting, vermicomposting, microbial inoculation, anaerobic digestion and thermochemical methods, are critically evaluated. The review also highlights the role of beneficial microorganisms in nutrient transformation and recovery, as well as emerging technologies such as biochar-based fertilisers, electrochemical nutrient recovery systems and integrated sludge biorefineries. Findings from laboratory and field studies demonstrate that sludge-derived biofertilisers can enhance soil fertility, improve microbial activity, increase nutrient availability and support crop productivity while reducing dependence on synthetic fertilisers. However, issues related to heavy metals, organic contaminants, pathogen removal, product quality and regulatory compliance remain important challenges. Overall, the bioconversion of agro-industrial sludge into biofertilisers offers a promising pathway for sustainable waste management, resource recovery, environmental protection and resilient agricultural development.

The integration of Remote Sensing (RS) and Geographic Information Systems (GIS) has transformed agricultural monitoring and extension services by enabling real-time, location-specific, and data-driven decision-making. This study explores the conceptual framework, technologies, and practical applications of RS and GIS in monitoring crop health, predicting yield, and delivering adaptive agri-advisories. It highlights the capabilities of satellite imagery, UAVs, hyperspectral and thermal imaging, and their integration within GIS platforms to support sustainable and precision agriculture. The paper reviews notable initiatives such as India’s FASAL project and platforms like GeoFarmer, which demonstrate the effectiveness of geospatial tools in improving farm-level interventions. Furthermore, the study examines the growing role of Artificial Intelligence and Big Data in enhancing the accuracy and reach of extension services. Despite these advances, challenges persist, including high costs, technical capacity gaps, limited rural infrastructure, and the need for better socio-economic data integration. The paper concludes with future directions and policy implications, emphasizing the need for investment in digital infrastructure, training, open-data access, and public-private partnerships to make RS-GIS-based agriculture more inclusive, resilient, and impactful.