Crop yield prediction using multi-parametric deep neural networks

Objective: To propose Multi-parametric Deep Neural Network (MDNN) for modeling the impact of climate changes, multiple parameters related to weather and soil accurate crop yield prediction. Methods: In MDNN, a measure called Growing-Degree Day (GDD) is introduced measuring overall effect conditions yield. One key elements in MDNN neuron’s layer-wise activation function. order enhance predictive performance, leaky rectified linear unit used units MDNN. For analysis performance DNN data about weather, are collected from http://www.ccafs-climate.org/climatewizard/, https://data.world/thatzprem/agriculture-india https://data.gov.in/search/site?query=soil respectively. From data, 60000 records training 40,000 testing. Findings: By considering on yield, accuracy improved predicting The effectiveness tested compared with different types crops. achieves 91.84% mean five crops classification. Novelty: This proposed work tries predict more accurately by analyzing climate, parameters. considerably improves statistical efficiency over typical using previous knowledge important phenomena functional forms relating them Keywords: Crop prediction; machine learning; DNN; climatic changes; parameters; growing degree-day