Abstract: Crop yield prediction is an important area of research that involves analyzing environmental, soil, water, and crop parameters. Deep-learning models have gained popularity for extracting meaningful crop features to make accurate predictions. However, these methods have certain limitations. They are unable to establish a direct relationship, whether linear or nonlinear, between the raw data and crop yield values. Additionally, the performance of these models heavily relies on the quality of the extracted features. To overcome these drawbacks, deep reinforcement learning offers a solution. By combining the strengths of reinforcement learning and deep learning, deep reinforcement learning constructs a comprehensive framework for crop yield prediction. This framework effectively maps the raw data to the predicted crop values, addressing the aforementioned inadequacies.
Keywords: Deep learning, linear mapping, nonlinear mapping, prediction
|
DOI:
10.17148/IJARCCE.2023.125203
