Crop Production Estimation Using Remote Sensing

The ever-increasing global population demands a steep increase in food grain production. To cope up with this demand and maintain a steady supply, proper crop monitoring and production forecasting systems are some of the major requirements. Advance estimation of crop yield is useful for different stakeholders to plan standard agronomical practices, procurement, determine storage availability, transportation, price fixation, and marketing of agricultural products. This estimation can be done by statistical analysis using traditional ground-based study or by using remotely sensed data. The developments in the field of satellite and sensor technologies in the last few decades have established the second method as the most trusted and efficient tool to forecast crop production. Its time and cost-effectiveness with precise estimation capacity ascertain its competence. This chapter presents an exhaustive discussion on the role of these methods (particularly satellite remote sensing) in crop yield estimation. Analysis and transformation of space data to process different vegetation indices and their use in crop production estimation have been detailed. These vegetation indices are generally used as an explanatory variable in different traditional and advanced statistical models. Further, recent advancements in modeling techniques have introduced applications like machine learning, artificial intelligence, pattern recognition, mobile computing, etc., and thus opened a new dimension in production forecasting processes. This chapter also tried to focus on these rapidly evolving sectors and their possible contribution to the crop yield estimation.