Search

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 R2 and root mean square error (RMSE) of the models varied between 0.22-0.98 and 24.02-607.29 kg ha−1, 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−1 and 0.98-36.7%, respectively. For evaluation of multiple models for multiple locations statistically, overall average ranks on the basis of R2 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. [ABSTRACT FROM AUTHOR]

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. [ABSTRACT FROM AUTHOR]