Evaluating the efficiency of water development-utilization-treatment system in “One Belt and One Road” regions: A three stage DEA-BPNN model

With the rapid economic growth and urbanization, water shortage and water pollution are becoming more and more serious. It is of great significance for decision makers to get the efficiency of the water system and know its development trend. Data Envelopment Analysis (DEA) stands as a robust tool for assessing efficiency. However, the DEA model lacks predictive capabilities, which can't give guidance for future development. In contrast, the Back Propagation Neural Network (BPNN) offers powerful nonlinear mapping and adaptive prediction capabilities. To compensate for the deficiencies of the DEA model, the three stage DEA-BPNN model is developed based on environmental compatibility and economic development. This model enables specific efficiency measurements, identifies system weaknesses, and anticipates future trends. Then, the proposed model is applied to the “One Belt And One Road” region, comparing its predictive performance with that of linear regression, generalized additive model, support vector machines, k-nearest neighbors, random forest, and gradient boost decision trees. As a result, among the determination of several prediction models, the BPNN model obtains more accurate prediction results.