Crop Type Classification Using Deep Learning

Abstract

Crop type classification is one of the important part of many applications in food security and agricultural monitoring. Due to rapidly enhancement in the field of science and technology, satellites sensors are getting more powerful, thats why remote sensing images are providing more information in spatial and temporal resolution. Satellites are becoming powerful for crop type maping. Automation crop type mapping is still very challenging due to lack of ground truth data for training supervised classification models. New satellite sensors acquire remote sensing images in high spatial and spectural images of the world. Combination of the spatial,spectral and temporal resolutions of remote sensing images enables the vegetation dynamics monitoring. Traditional classification algorithms, such as Random Forest (RF), have been successfully applied for Crop Type Classification in remote sensing images. There are several advantages of remote sensing in the field of agriculture. Each year Pakistan loses tons of its crop production due to poor farming practices. These technologies have many applications in the field of agriculture such as crop growth monitoring, crop acreage estimation, soil moisture estimation, soil fertility evaluation, and flood condition monitoring, detection of diseases and pest infestation, yield estimation, precise and accurate information of agriculture is required for maintaining the sustainability of the agricultural systems and improving the economic growth of the country