Abstract
This study proposes an intelligent IoT-based framework for forecasting crop damage in smart agricultural systems. Integrating smart farming with machine learning (ML) to comprehend the complex relationships in agriculture requires access to comprehensive and coherent datasets. However, such datasets are often incomplete due to missing data across various input features, posing a challenge for developing robust predictive models using ML. Addressing the issue of missing data is critical throughout the development, evaluation, and implementation phases of predictive models in smart farming. While ML methods are commonly believed to handle missing data well, their applicability in agriculture research remains unclear. This study aims to assess how ML-based prediction model studies address missing data and to what extent. To systematically explore the performance and applicability of both single ML algorithms and ensemble learning (EL) algorithms, this study adopts appropriate criteria for assessing missing data treatment in decision-making processes. The performance of various missing data processing techniques varies across different scenarios of missing data. Overall, ensemble learning demonstrates superior imputation performance compared to traditional ML methods, particularly in scenarios with high correlations among missing features. Among the ensemble learning algorithms evaluated, XGBoost, CatBoost, and LGBM classifiers with hyperparameter optimization exhibit notable performance, surpassing that of linear regression. Specifically, the XGBoost classifier achieves average sensitivity, accuracy, precision, and F-score values of 88.1, 89.56, 83.4, and 84.8, respectively. Similarly, the CatBoost classifier attains values of 88.1, 90.50, 83.3, and 84.6 for the same metrics. In comparison, the LGBM classifier achieves values of 86.3, 90.23, 81.1, and 83.1 for sensitivity, accuracy, precision, and F-score, respectively. Moreover, the accuracy of predicting missing values is assessed using Mean Squared Error (MSE) and R-squared (R2), with the XGBoost model demonstrating notably low MSE (0.0213) and high R2 (0.99), indicative of its strong performance in this aspect.