Crop Predictive Insights: The Synergy of Deep Learning, Multi-Source Satellite Imagery and Weather Data

• Published in: IGARSS 2023 - 2023 IEEE International Geoscience and Remote Sensing Symposium pp. 3554 - 3557
• Main Authors: Patel, Pragneshkumar, Chaudhary, Sanjay, Parmar, Hasit
• Format: Conference Proceeding
• Language: English
• Published: IEEE 16.07.2023
• Subjects: Convolution; Convolutional Neural Network; Crop Yield; Crops; Data models; Deep learning; Landsat-7; Long Short-Term Memory; MODIS; Predictive models; Recurrent neural networks; Soil; Weather; Wheat
• ISSN: 2153-7003
• DOI: 10.1109/IGARSS52108.2023.10283245

Crop yield prediction is affected by many factors such as weather, soil, crop cultivation and management practices, climate change and impact of different factors vary based on the different crops and regions. Crop growth can be captured by analyzing satellite images collected over a period using deep learning methods. To recognize the influence of weather on the crop growth, we applied convolution neural network (CNN)-long short term memory (LSTM) and convolution neural network(CNN)-recurrent neural network (RNN) based models on the satellite images. To capture robust growth over the duration, we had taken fusion of MODIS and LANDSAT-7 images along with weather data and observed results. The forecasting results of CNN-LSMT model shows more than 5% of performance improvement with weather data compared to without it. Other model also shown better results when applied with weather data. It exhibits strong correlation of weather with the crop growth.