Machine Learning for Sustainable Development: A Comprehensive Review of Applications in Energy Efficiency, Climate Modeling, and Waste Management Journal

This review has conducted a systematic survey of machine learning applications in the three most computationally feasible dimensions of sustainable development: energy efficiency, climate modeling and waste reduction. The reviewed body of evidence shows that ML has outgrown proof-of-concept works to prove useful operational applications in practical applications - in Pangu-Weather by operational-level weather forecasts to automated sorting systems in manufacturing recycling plants. Among the important findings: (1) RMSE scores of household energy forecasting tasks with well-engineered autoregressive features are reduced by more than 90% by random Forest models and LSTM models; (2) CNN-LSTM hybrids cannot be reduced by more than 60% over statistical baselines; (3) ResNet-50 can be used to achieve over 90% accuracy in waste classification with six All these findings support the thesis statement that machine learning is a pragmatically implementable enabling technology to the UN SDGs, especially SDG 7, SDG 12 and SDG 13. The way ahead lies in solving data quality issues, creating physically constrained architectures, rolling out to resource-constrained settings, and creating strong governance frameworks of AI in sustainability. The intersection of edge computing, federated learning, and explainable AI and domain-specific sustainability knowledge is the most promising avenue to scalable, equitable, and trustworthy AI-driven sustainable development.

[1]    Kaifeng Bi, Lingxi Xie, et al. 'Accurate medium-range global weather forecasting with 3D neural networks.' Nature, Vol. 619, 2023. https://doi.org/10.1038/s41586-023-06185-3 [2]    Atit Bashyal, Tina Boroukhian. 'Multi-agent deep reinforcement learning based demand response and energy management for heavy industries.' Applied Energy, 392, 2025. https://doi.org/10.1016/j.apenergy.2025.125990 [3]    Ricardo Vinuesa, Hossein Azizpour, et al. 'The role of artificial intelligence in achieving the Sustainable Development Goals.' Nature Communications, 2020. https://doi.org/10.1038/s41467-019-14108-y [4]    Bingbing Fang, Jiacheng Yu, et al. 'Artificial intelligence for waste management in smart cities: a review.' Environmental Chemistry Letters, 21, 2023. https://doi.org/10.1007/s10311-023-01604-3 [5]    Gatti A., Barbierato E., Pozzi A. 'Toward Greener Smart Cities: A Critical Review of Classic and Machine-Learning-Based Algorithms for Smart Bin Collection.' Electronics, 13(5), 836, 2024. [6]    Prabadevi Boopathy, Madhusanka Liyanage, et al. 'Deep learning for intelligent demand response and smart grids: A comprehensive survey.' Computer Science Review, 2024. [7]    Biswajit Biswal, Subhasish Deb, et al. 'Review on smart grid load forecasting for smart energy management using machine learning and deep learning techniques.' Energy Reports, 12, 2024. [8]    David Weinberg, Qian Wang, et al. 'A Review of Reinforcement Learning for Controlling Building Energy Systems From a Computer Science Perspective.' Sustainable Cities and Society, 89, 2023. [9]    Zhong X., Zhang Z., et al. 'End-to-End Deep Reinforcement Learning Control for HVAC Systems in Office Buildings.' Designs, 6(3), 52, 2022. [10] LeCun Y., Bengio Y., Hinton G. 'Deep learning.' Nature, 521(7553), 436–444, 2015.