Integrating CA–Markov–ANN for spatiotemporal prediction of land use dynamics in a fragile Himalayan watershed

Predicting future Land-Use/Land-Cover (LULC) changes is essential for sustainable resource management and environmental monitoring, particularly in ecologically fragile high-altitude Himalayan watersheds like the Parbati Watershed (PW), where biodiversity, hydrology, and climate stability are increasingly threatened. However, limited studies have explored integrated, data-driven LULC modeling approaches for high-altitude Himalayan watersheds, leaving a critical gap in understanding the spatiotemporal evolution of these sensitive landscapes. This study addresses this gap by proposing a novel Cellular Automata (CA)-Markov chain (MC)-based Artificial Neural Network (CA–MC-ANN) framework, implemented through a Multi-Layer Perceptron (MLP) prediction architecture and uniquely tailored to the PW. We assess past LULC dynamics (1989–2023) and project future scenarios (2035, 2045) to understand transformations driven by intertwined anthropogenic pressures and climate change. Key findings reveal a rapidly transforming landscape where glacier/snow cover has decreased from ∼37.66% (1989) to ∼21.61% (2023), projected to fall to ∼13.47% by 2045—a ∼24.19% cumulative loss (∼-0.43%/yr) driven by high-altitude warming. In contrast, built-up/settlement areas increased from ∼0.26% (1989) to ∼0.80% (2023) and are projected to reach ∼1.21% by 2045—a ∼0.95% cumulative gain (∼+0.02%/yr), reflecting tourism boosts, hydroelectric projects (HEPs), and rapid infrastructure expansion. Alongside, Himalayan Moist Temperate Forests (HMTF) declined from ∼14.95% (1989) to ∼14.06% (2023) and are also projected to decline to ∼13.75% by 2045—a ∼-1.20% cumulative loss (∼-0.02%/yr), indicating mounting pressure on natural ecosystems. These trends highlight accelerating glacial shrinkage, rapid tourism and development expansion, and land degradation. These findings underscore the urgent need for integrated spatial analysis and predictive modelling to inform regional conservation, sustainable land management, and resilient development strategies. Implementing comprehensive LULC and biodiversity impact assessments is critical for enhancing environmental resilience and ensuring long-term socio-ecological sustainability in the ecologically sensitive Himalayan region. • Analyzed LULC change in Parbati Watershed (1989–2023) using multi-temporal satellite data. • Evaluated past trends and projected futures with integrated CA–Markov–ANN modeling. • Simulated 2035/2045 LULC using CA–Markov–ANN, SVM outputs, and AHP transition weights. • Built-up areas projected to increase by +0.95%, showing intensified development growth. • Glacier/snow cover projected to decline by −24.19%, signaling rapid glacial retreat.