Hilal Ahmad

Reservoir-induced landslides threaten infrastructures and downstream communities, making continuous deformation monitoring vital. Time-series InSAR, notably the SBAS algorithm, provides high-precision surface-displacement mapping but suffers from voids due to layover/shadow effects and temporal decorrelation. Existing deep-learning approaches often operate on fixed-size patches or ignore irregular spatio-temporal dependencies, limiting their ability to recover missing pixels. With this objective, a hybrid spatio-temporal Graph Attention (ST-GAT) framework was developed and trained on SBAS-InSAR values using 24 influential features. A unified spatio-temporal graph is constructed, where each node represents a pixel at a specific acquisition time. The nodes are connected via inverse distance spatial edges to their K-nearest neighbors, and they have bidirectional temporal edges to themselves in adjacent acquisitions. The two spatial GAT layers capture terrain-driven influences, while the two temporal GAT layers model annual deformation trends. A compact MLP with per-map bias converts the fused node embeddings into normalized LOS estimates. The SBAS-InSAR results reveal LOS deformation, with 48% of missing pixels and 20% located near the Dasu dam. ST D-GAT reconstructed fully continuous spatio-temporal displacement fields, filling voids at critical sites. The model was validated and achieved an overall R² (0.907), ρ (0.947), per-map R² ≥ 0.807 with RMSE ≤ 9.99, and a ROC-AUC of 0.91. It also outperformed the six compared baseline models (IDW, KNN, RF, XGBoost, MLP, simple-NN) in both RMSE and R². By combining observed LOS values with 24 covariates in the proposed model, it delivers physically consistent gap-filling and enables continuous, high-resolution landslide monitoring in radar-challenged mountainous terrain.

Mining activities in Pakistan’s mineral-rich provinces threaten freshwater security through groundwater depletion, contamination, and flood-induced pollution. This study develops an Inclusive Disaster Risk Reduction (IDRR) framework integrating governance, social, environmental, and technical (GSET) dimensions to holistically assess mining-induced water hazards across Balochistan, Khyber Pakhtunkhwa, and Punjab. Using GIS-based spatial risk mapping with multi-layer hydrological modeling, we combine computational analysis and participatory validation to identify vulnerability hotspots and prioritize high-risk mines. Community workshops involving women water collectors, indigenous leaders, and local experts enhanced map accuracy by translating indigenous knowledge into spatially referenced mitigation plans and integrating gender-sensitive metrics to address gendered water access disparities. Key findings reveal severe groundwater depletion, acid mine drainage, and gendered burdens near Saindak and Cherat mines. Multi-sectoral engagements secured corporate commitments for water stewardship and policy advances in inclusive governance. The framework employs four priority-ranked risk categories (Governance-Economic 15%, Social-Community 30%, Environmental 40%, Technical-Geological 15%) derived via local stakeholder collaboration, enabling context-specific interventions. Despite data limitations, the GIS-driven methodology provides a scalable model for regions facing socio-environmental vulnerabilities. The results demonstrate how community participation directly shaped village-level water management alongside GSET analysis to craft equitable risk reduction strategies. Spatially explicit risk maps guided infrastructure upgrades and zoning regulations, advancing SDG 6 and 13 progress in Pakistan. This work underscores the value of inclusive, weighted frameworks for sustainable mining–water nexus management in Pakistan and analogous contexts.

The transition from open pit to underground mining intensifies water-related hazards such as Acid Mine Drainage (AMD), groundwater contamination, and aquifer depletion, threatening ecological and socio-economic sustainability. This study develops an Inclusive Disaster Risk Reduction (IDRR) framework using a Multi-Dimensional Risk (MDR) approach to holistically assess water hazards in China’s mining regions, integrating environmental, social, governance, economic, technical, community-based, and technological dimensions. A Multi-Criteria Decision-Making (MCDM) model combining the Fuzzy Analytic Hierarchy Process (AHP) and Technique for Order Preference by Similarity to Ideal Solution (TOPSIS) evaluates risks, enhanced by a Z-number Fuzzy Delphi AHP (ZFDAHP) spatiotemporal model to dynamically weight hazards across temporal (short-, medium-, long-term) and spatial (local to global) scales. Applied to the Sijiaying Iron Mine, AMD (78% severity) and groundwater depletion (72% severity) emerge as dominant hazards exacerbated by climate change impacts (36.3% dynamic weight). Real-time IoT monitoring systems and AI-driven predictive models demonstrate efficacy in mitigating contamination, while gender-inclusive governance and community-led aquifer protection address socio-environmental gaps. The study underscores the misalignment between static regulations and dynamic spatiotemporal risks, advocating for Lifecycle Assessments (LCAs) and transboundary water agreements. Policy recommendations prioritize IoT adoption, carbon–water nexus incentives, and Indigenous knowledge integration to align mining transitions with Sustainable Development Goals (SDGs) 6 (Clean Water), 13 (Climate Action), and 14 (Life Below Water). This research advances a holistic strategy to harmonize mineral extraction with water security, offering scalable solutions for global mining regions facing similar ecological and governance challenges.

The purpose of this study is to assess the landslide risk for Hunza–Nagar Valley (Northern Pakistan). In this study, different conditioning factors, e.g., topographical, geomorphological, climatic, and geological factors were considered. Two machine learning approaches, i.e., logistic regression and artificial neural network were used to develop landslide susceptibility maps. The accuracy test was carried out using the receiving operative characteristic (ROC) curve. Which showed that the success and prediction rates of LR model is 82.60 and 81.60%, while 77.90 and 75.40%, for the ANN model. Due to the physiographic condition of the area, the rainfall density was considered as the primary triggering factor and landslide index map was generated. Moreover, using the Aster data the land cover (LC) map was developed. The settlements were extracted from the LC map and used as the elements at risk and hence, the vulnerability index was developed. Finally, the landslide risk map (LRM) for the Hunza–Nagar valley was developed. The LRM indicated that 37.25 (20.21 km²) and 47.64% (25.84 km²) of the total settlements lie in low and very high-risk zones. This landslide risk map can help decision-makers for potential land development and landslide countermeasures.