AAT-SCYP: Advance Agriculture Technology for sustainable crop yield prediction and environmental sustainability using Machine Learning Algorithms

Advanced Agricultural Technology (AATs) is a formidable crop yield prediction system that can predict crop yield by enabling more sustainable and efficient agricultural strategies. AAT works in two ways: to predict crop yield and to ensure sustainability. We focus on efficient land use, accurately predicting crop yields, optimizing planting decisions, adaptation to climate change, and helping farmers choose climate-resilient crops for a sustainable environment and to play a role in the fourth generation agricultural revolution. Traditional methods of predicting crop yield often rely on statistical models or systems based on expert knowledge, which have limitations in capturing complex relationships and adapting to changing conditions. One unique aspect of our research is the inclusion of a Bangladeshi dataset obtained from Bangladesh Agriculture Research Institute (BARI), which focuses on the agricultural conditions and crop yields in Bangladesh. We have collected an agricultural dataset from the BARI , an Open-source dataset from Kaggle, and a hybrid dataset. Here, pre-processing techniques are utilized to enhance the model’s performance. The one-hot encoding is used for encoding the categorical features and normalizing numerical features. AATs uses a variety of machine learning algorithms such as logistic regression (LR), random forest (RF), XG-Boost, and Support Vector Machine (SVM) to predict crop yield for the following year and evaluate their performance. The RF model achieved an accuracy of approximately 96.62% in the Bangladeshi dataset, 99.31% in the Indian dataset, and 95.03% in the hybrid dataset. This emphasizes the efficiency of RF in accurately predicting crops based on the given plants. In this research, we develop a model that can predict crop dividends more efficiently, strongly, and with high accuracy when using a separate machine learning -based algorithm.