Machine Learning based Predictive Assessments of Impacts of Influential Climatic Conditions for the Sustainable Productivity of Paddy Crops

S Thirumal, Latha R

International Journal of Electronics and Communication Engineering · 31 May 2023

In one sentence. Multiplicative LSTM models project climate-change effects on paddy rice production in a region of interest; a regional application with limited methodological novelty.

Abstract

The excessive inundation of paddy fields and the consumption of groundwater, fertilizers, and insecticides have resulted in substantial unintended consequences. The trajectory of the weather patterns and the correlation between weather and harvests will determine these effects' unique character and scale. Considering the essential environmental concerns affecting paddy ecosystems, this study aims to give a predictive evaluation and outline the ecological implications of rice production and the influence of a changing climate on paddy cultivation in the Region of Interest (RoI). In addition to these realities, it is essential to foresee the climate's effect on paddy fields by employing forward-thinking solutions for dealing with the ever-changing weather patterns that may directly impact rice yields. Philosophy-wise, Machine Learning (ML) differs from most traditional statistics since it emphasizes forecasting rather than description. In this paper, the case study centred on the findings of geographic climate models is conducted using multiplicative Long-Short Term Memory (mLSTM). mLSTM is employed to evaluate the consequences of climatic or environmental changes on rice production in RoI, showing the novelty of the work. To assess the effectiveness of the proposed methodology, the predicted outcomes are compared with the actual results. Sustainable rice production is assured through reasonable and actionable guidelines in the face of mounting environmental challenges.

Labels

Labels and summary are generated by Claude and reviewed weekly. Wrong? Edit this entry.