Emerging market growth and environmental trade-offs in the Indian Ocean region: A machine learning-based predictive analysis of IORA countries

Emerging Market Growth and Environmental Trade-offs in the Indian Ocean Region

Against the backdrop of the global South's rise, countries along the Indian Ocean are becoming the front line of the contradiction between economic growth and environmental protection. A recent study published in *Scientific Reports* (Xu et al., 2026) focuses on four countries—Malaysia, Mauritius, Sri Lanka, and Madagascar—using machine learning models to predict GDP and agricultural land area, revealing the complex relationships between economic development, CO2 emissions, and land change. This research not only provides a scientific tool for regional policymakers but also reflects the sustainability challenges faced by emerging markets in their pursuit of growth.

#### Regional Structure: Vulnerability and Opportunities of Coastal Economies

IORA (Indian Ocean Rim Association) covers 23 member states across Africa, the Middle East, South Asia, and Southeast Asia, many of which are island or coastal nations highly sensitive to climate change. The four selected countries represent different stages of development: Malaysia, as a manufacturing hub in Southeast Asia, has economic growth closely tied to industrial emissions; Mauritius is a successful transformation case in Africa with a tourism and financial services economy; Sri Lanka is dominated by South Asian agriculture and textiles; while Madagascar faces pressures from agricultural expansion and deforestation. Together, these four countries form a microspectrum, illustrating the typical tension between industrialization and ecological protection in emerging markets.

#### Data-Driven Policy Tools

Traditional economic-environmental models are often computationally complex and parameter-sensitive. The XOS-ELM-GA model proposed in this study improves prediction accuracy significantly through genetic algorithm optimization and Xavier weight initialization. For example, in Malaysia's GDP prediction, the model achieved an average SMAPE of only 10.13%, while in Sri Lanka's agricultural land prediction, the SMAPE was as low as 3.77%. Such high-accuracy forecasting is particularly important for emerging market countries with limited funding and weak data foundations—they can predict economic and land change trends based on historical emission data without building large-scale earth system models.

#### Investment Perspective: From Emissions to Growth Signals

For international investors, carbon emission indicators are shifting from an environmental external variable to a leading indicator of economic structural transformation. Prediction results for Malaysia and Mauritius show a strong nonlinear correlation between CO2 emissions and GDP, suggesting that emission growth during the industrialization phase may accompany economic expansion, while decoupling may accelerate once the service sector becomes dominant. In contrast, agricultural land changes in Sri Lanka and Madagascar are more closely linked to emissions, reflecting the dependence of agricultural economies on natural resources. Investors can use this to assess the sustainability of growth models across different economies and identify policy risks and transformation opportunities.

#### Long-term Trends and the Global South AgendaThe study highlights that IORA countries need to balance SDG 8 (economic growth), SDG 13 (climate action), and SDG 15 (life on land). This is precisely a common dilemma for many Global South nations: rapid urbanization and industrialization require energy consumption, while climate resilience demands emission reductions. The predictive capability of machine learning can help countries set emission caps or agricultural expansion boundaries in advance, avoiding the "pollute first, treat later" path. From a regional cooperation perspective, technology sharing under the IORA framework (such as the model proposed in this study) can provide low-cost decision support for other developing countries.

#### Conclusion

The technical contribution of this study lies in providing a reusable predictive tool for emerging markets, while its broader significance is to translate the environment-economy interplay into quantifiable policy choices. As the Indian Ocean corridor becomes a vital part of global trade and supply chains, the growth trajectories of countries like Malaysia and Mauritius will influence developmental models in surrounding regions. Investors and policymakers alike should pay attention to how these countries leverage data science to strike a balance between growth and green—this is not only an environmental issue but also the core of long-term competitiveness for emerging markets.