Machine Learning approach to Predict net radiation over crop surfaces from global solar radiation and canopy temperature data.

As the ground-based instruments for measuring net radiation are costly and need to be handled skillfully, the net radiation data at spatial and temporal scales over Indian subcontinent are scanty. Sometimes, it is necessary to use other meteorological parameters to estimate the value of net radiation, although the prediction may vary based on season, ground cover and estimation method. In this context, artificial intelligence can be used as a powerful tool for predicting the data considering past observed data. This paper proposes a novel method to predict the net radiation for five crop surfaces using global solar radiation and canopy temperature. This contribution includes the generation of real-time data for five crops grown in West Bengal state of India. After manual analysis and data preprocessing, data normalization has been done before applying machine learning approaches for training a robust model. We have presented the comparison in various machine learning algorithm such as ridge and spline regression, random forest, ensemble and deep neural networks. The result shows that the gradient boosting regression and ridge regression are outperforming other ML approaches. The estimated predictors enable to reduce the number of resources in terms of time, cost and manpower for proper net radiation estimation. Thus, the problem of predicting net radiation over various crop surfaces can be sorted out through ML algorithm.

Evaluating the long-term impact of projected climate on rice-lentil-groundnut cropping system in Lower Gangetic Plain of India using crop simulation modelling.

Most simulations of food production in response to various climates to date have used simulations of the same crop over multiple years. This study evaluated the impact of projected climate on performance of rice-lentil-groundnut cropping sequence in New Alluvial Zone of West Bengal, India, using DSSAT model. The study period consisted of baseline (1980-2010), mid-century (2040-2069) and end-century (2070-2099). Advancement in days to anthesis (2-13 days) was simulated for rice during the future periods. For lentil and groundnut, average advancement in days to anthesis was 1 day. Days to maturity were shortened by 3-16 days for rice and 0-7 days for lentil. Nevertheless, for groundnut, the days to maturity were simulated to increase by 1-9 days. The impact on final biomass and yield was simulated with and without CO2 fertilization, and the positive impact of CO2 fertilization was prominent for all the three crops. When CO2 fertilization effect was considered, the yield of rice was projected to increase by 11-32%. On the other hand, yield of lentil and groundnut was estimated to change by - 31 to - 12% and - 33 to + 8%, respectively. Enhanced CO2 could mitigate the magnitude of yield reduction due to enhanced temperature. Rice was benefited due to the carryover effect of residue from preceding groundnut and, hence, could sustain the yield on a long term. The study could also quantify the uncertainty in simulation of yield due to selection of GCMs.