Retrieval of Crop Biophysical Parameters Using Remote Sensing

Consistent and near-real-time crop growth monitoring over a large scale is a very crucial step for digital agriculture. An efficient tool for accurate retrieval of different biophysical parameters is the basic requirement for crop growth monitoring. Quantitative estimation of various crop biochemical and biophysical variables with reliable accuracy is very useful for different applications related to agriculture, ecology, and climate. This chapter briefly describes different methods and models for the retrieval of various crop biophysical parameters using remote sensing (RS) approaches. Leaf area index (LAI) is a vital attribute in many land-surface vegetation and climate models which have many important applications. Leaf chlorophyll and leaf water content are key parameters in many ecological processes, such as photosynthesis, respiration, transpiration, and they also provide stress information. The fraction of absorbed photosynthetically active radiation (fAPAR) by crop vegetation is used as an essential climate variable (ECVs) and critical input in many land-surface, crop growth and climate, ecological, water, and carbon cycle models. This chapter highlights various retrieval methods of crop biophysical parameters, including empirical, semiempirical, hybrid, physically based models with various inversion algorithms like look-up table, neural network, genetic algorithms, Bayesian networks, support vectors, etc.