Efficient Crop Classification Using Optical and Radar Big Data: A Time and Cost Reduction Approach

The ability to accurately estimate crop numbers for various varieties of vegetables makes crop classification an essential component of agriculture. In order to meet the anticipated demand in the future, dealers can predict the number of crops sold on the market. For crop classification, scientists have recently used a variety of data sources, including optical (Polarimetric) and radar sensing imaging. They have, however, run into difficulties when working with huge, high-dimensional, and imbalanced datasets. Some researchers have used a 3-stacked generalization strategy to address these issues. This approach was difficult to train and tackling massive data and imbalanced data concerns head-on. They were able to get an F1-score of 85% with this technique. We used the regression feature selection technique and data sampling in our work, using only 20% of the total data as the training dataset. The effectiveness of our classification methods was significantly improved and the training time was much decreased by these preprocessing techniques. We specifically acquired a remarkable F1-score of 99% after just 42 seconds of training utilizing the Random Forest algorithm. We also achieved a respectable F1-score of 97% in under 7 seconds using Linear SVC. We also demonstrate that good performance may be achieved by using one day's worth of radar data with only 38 features to cut costs and time. The results show that we can use only 16 features to get high performance. In our research, we found that employing radar data produces outcomes that are higher performing and more accurate than using optical data. We have out extensive experiments to show the potency of our methods.