Rice is generally grown under completely flooded condition and providing food for more than half of the world's population. Any changes in weather parameters might affect the rice productivity thereby impacting the food security of burgeoning population. So, the crop yield forecasting based on weather parameters will help farmers, policy makers and administrators to manage adversities. The present investigation examines the application of stepwise multiple linear regression (SMLR), artificial neural network (ANN) solely and in combination with principal components analysis (PCA) and penalised regression models (e.g. least absolute shrinkage and selection operator (LASSO) or elastic net (ENET)) for rice yield prediction using long-term weather data. The R and root mean square error (RMSE) of the models varied between 0.22-0.98 and 24.02-607.29 kg ha, respectively during calibration. During validation with independent dataset, the RMSE and normalised root mean square error (nRMSE) ranged between 21.35-981.89 kg ha and 0.98-36.7%, respectively. For evaluation of multiple models for multiple locations statistically, overall average ranks on the basis of R and RMSE of calibration; RMSE and nRMSE of validation were calculated and non-parametric Friedman test was applied to check the significant difference among the models. The ranking of the models revealed that LASSO (2.63) was the best performing model followed by ENET (3.07) while PCA-ANN (4.19) was the worst model which was found significant at p < 0.001. The reason behind good performance of LASSO and ENET is that these models prevent overfitting and reduce model complexity by penalising the magnitude of coefficients. Then, pairwise multiple comparison test was performed which indicated LASSO as the best model which was found similar to SMLR and ENET. So, for prediction of rice yield, these models can very well be utilised for west coast of India.

Integrated farming systems (IFS) entail a holistic approach to farming aimed at meeting the multiple demands (impart farm resilience, farmer livelihoods, food security, ecosystem services, and making farms adaptive and resilient, etc.). IFS are characterized by temporal and spatial mixing of crops, livestock, fishery, and allied activities in a single farm. It is hypothesized that these complex farms are more productive at a system level, are less vulnerable to volatility, and produce less negative externalities than simplified farms. Thereby, they cater the needs of small and marginal farmers, who are the backbone of agriculture in India. Our review of literature shows that IFS have the potential to improve farm profitability (265%) and employment (143%) compared to single enterprise farms. The literature showed that IFS enhance nutrient recycling through composting, mulching, and residue incorporation and, as a consequence, have the capacity to reduce the external purchase of inputs. The nutrient recycling in turn helps to increase the soil quality indicators such as soil nutrient availability and also improves soil microbial activity. The IFS play a major role in biodiversity conservation through adoption of diversified cropping system and through integration of indigenous livestock breeds. IFS also played important role in improving soil organic carbon from 0.75 to 0.82%. Due to increased carbon sequestration, biomass production by trees, reduced consumption of fertilizers, and pesticides the greenhouse gas emission could be reduced significantly. This results in a linked system making it sustainable and climate‐resilient. The main challenge associated with adoption of IFS is it requires skill, knowledge, resources, labor, and capital which are not always available with small and marginal farmers. There is a need for integrating productivity, profitability, and environmental sustainability variables in a single evaluation framework to effectively generate information toward enhancing adaptability of IFS.

Protected cultivation is an innovative way of raising seasonal and off-seasonal crops under a controlled environment. Vegetables and flower crops have tremendous potential to augment productivity, generate employment, utilize land efficiently and enhance export. This study was undertaken to assess the economic feasibility of protected cultivation in the high export potential zones of the Pune and Nasik districts of Maharashtra, India, by employing project analytical tools and the regression model. The results revealed that the cultivation of flowers and vegetables under protected cultivation was highly lucrative with high investment. The protected cultivation of rose and capsicum had higher cultivation cost (300%), gross return (250%) and net return (190%) as compared to open cultivation. Moreover, most of the crops grown in polyhouses are highly profitable at different discount rates (7%, 10% and 12%), whereas a few crops were rewarding under shade net condition with subsidies. Factors such as literacy (p < 0.05), income (p < 0.05), access to subsidy (p < 0.05) and the risk orientation index (p < 0.01) were found statistically significant in technology adoption. In the context of a changing climate and shrinking land resources, water scarcity, incidence of pests and diseases, an ever-increasing population, low productivity under open conditions and changes in consumer’s preference are the drivers for switching over to protected cultivation. In the recent past, protected cultivation has been gaining importance in different parts of the country, including Maharashtra. The policy implications are creating modern infrastructure, enhanced application of ICTs, maximum crop production with minimum utilization of land and institutional support to promote technology on a commercial scale.

Climate change is viewed as the main obstacle to agricultural development in developing countries. The high dependence on agriculture and allied sectors makes many countries vulnerable to the climate change phenomenon. There is a gap in macro and micro-level understanding of climate change. Thoughtful farmers’ perceptions and impacts of climate change on farming are fundamental for developing various mitigation and adaptation strategies. Therefore, the main aim of the present study was to understand the pattern of climate variability, farmers’ perceptions about climate change, and farmers’ adaptation strategies based on their socio-cultural background in the villages of Goa, on the west coast of India. The results reveal that about 62% of the sampled farmers have experienced climate change in terms of meteorological indicators such as increased average temperature, decreased total rainfall, delayed onset of monsoon, and an increase in the length of the summer season. The temperature trend analysis (0.009 °C/year) validated farmers’ perceptions, while the perception of rainfall differed (−1.49 mm/year). Farmers are convinced that climate change has affected their farming (declining crop and livestock productivity, water depletion, and other related farm operations). They strive to adapt to climate change through crop diversification, an integrated crop-livestock system, contingency crop planning, and the adaptation of new crops and varieties. This study could be helpful for policymakers to establish a climate-resilient agriculture system by ensuring timely availability of farm inputs, accurate weather forecasting, and encouraging insurance products for crop and livestock enterprises, which will help farmers cope with the changing climate to enhance their income and economic wellbeing. Further, adaption of integrated farming, agroforestry, and indigenous technical knowledge is imperative to combat the ill effects of climate change.