Forecasting India's Demographic Transition Under Fertility Policy Scenarios Using hybrid LSTM-PINN Model

TL;DR

This paper introduces a hybrid LSTM-PINN model to forecast India's demographic changes from 2024 to 2054 under various fertility policy scenarios, capturing complex age-structured population dynamics.

Contribution

The study develops a novel hybrid modeling framework combining physics-informed neural networks with LSTM to improve demographic forecasting accuracy and interpretability.

Findings

Fertility policies significantly influence future age distribution and dependency ratios.

Stricter population control accelerates aging and reduces workforce participation.

Relaxed policies increase population pressure but support workforce growth.

Abstract

Demographic forecasting remains a fundamental challenge for policy planning in rapidly evolving nations such as India, where fertility transitions, policy interventions, and age structured dynamics interact in complex ways. In this study, we present a hybrid modelling framework that integrates policy-aware fertility functions into a Physics-Informed Neural Network (PINN) enhanced with Long Short-Term Memory (LSTM) networks to capture physical constraints and temporal dependencies in population dynamics. The model is applied to India's age structured population from 2024 to 2054 under three fertility-policy scenarios: continuation of current fertility decline, stricter population control, and relaxed fertility promotion. The governing transport-reaction partial differential equation is formulated with India-specific demographic indicators, including age-specific fertility and mortality rates. PINNs embed the core population equation and policy-driven fertility changes, while LSTM layers improve long-term forecasting across decades. Results show that fertility policies substantially shape future age distribution, dependency ratios, and workforce size. Stricter controls intensify ageing and reduce labour force participation, whereas relaxed policies support workforce growth but increase population pressure. Our findings suggest that the hybrid LSTM-PINN is an effective approach for demographic forecasting, offering accuracy with interpretability. Beyond methodological novelty, this work provides actionable insights for India's demographic policy debates, highlighting the need for balanced fertility interventions to ensure sustainable socio-economic development.