Statistics, Data Science, and Computing for Sustainable Development: Analytical Modeling and Decision Support in Life Sciences, Environment, and Society — A Systematic Review

Sustainable development requires robust analytical tools to address complex socio-ecological challenges. Statistics, data science, and computing are increasingly applied, yet the literature remains fragmented across disciplines. A systematic literature review was conducted following PRISMA guidelines. Scopus was searched for publications from 2016 to 2026. Inclusion criteria required studies applying statistical, data science, computing, or analytical modeling methods to sustainable development within life sciences, environment, or society. Data extraction and quality assessment using seven criteria were performed. A thematic synthesis was organized around five research questions. Twenty-nine studies met the inclusion criteria. All achieved high quality assessment scores (12–14 out of 14). The studies originated from twelve distinct author backgrounds, including business, plant biology, environmental science and natural resources, coastal and marine studies, soil science, statistics and data science, chemistry, and agriculture and post-harvest technology. This diversity reflects the multidisciplinary nature of the field. Studies spanned agriculture, water, climate, health, infrastructure, business, and decision science. Dominant methods included machine learning, deep learning, multi-criteria decision-making, optimization, and bibliometric analysis. Decision support systems were developed for policy, resource allocation, and risk management. Contributions to environmental, social, and economic sustainability were identified. Trends showed growth after 2018 and integration with Internet of Things, blockchain, and big data. Persistent gaps included data quality, standardization, interpretability, ethics, and the digital divide. Sustainability indicators frequently referenced the Sustainable Development Goals, environmental, social, and governance frameworks, circular economy, and life cycle assessment. Statistics, data science, and computing significantly contribute to sustainable development, but fragmentation and ethical concerns remain. Future research should prioritize standardized benchmarks, explainable artificial intelligence, cross-disciplinary collaboration, and real-world validation to ensure equitable and scalable solutions.