Among natural hazards, landslides are devastating in China. However, little is known regarding potential landslide-prone areas in Maoxian County. The goal of this study was to apply four deep learning algorithms, the convolutional neural network (CNN), deep neural network (DNN), long short-term memory (LSTM) networks, and recurrent neural network (RNN) in evaluating the possibility of landslides throughout Maoxian County, Sichuan, China. A total of 1290 landslide records was developed using historical records, field observations, and remote sensing techniques. The landslide susceptibility maps showed that most susceptible areas were along the Minjiang River and in some parts of the southeastern portion of the study area. Slope, rainfall, and distance to faults were the most influential factors affecting landslide occurrence. Results revealed that proportion of landslide susceptible areas in Maoxian County was as follows: identified landslides (13.65–23.71%) and non-landslides (76.29–86.35%). The resultant maps were tested against known landslide locations using the area under the curve (AUC). This study indicated that the DNN algorithm performed better than LSTM, CNN, and RNN in identifying landslides in Maoxian County, with AUC values (for prediction accuracy) of 87.30%, 86.50%, 85.60%, and 82.90%, respectively. The results of this study are useful for future landslide risk reduction along with devising sustainable land use planning in the study area.

The China–Pakistan Economic Corridor (CPEC) project passes through the Karakoram Highway in northern Pakistan, which is one of the most hazardous regions of the world. The most common hazards in this region are landslides and debris flows, which result in loss of life and severe infrastructure damage every year. This study assessed geohazards (landslides and debris flows) and developed susceptibility maps by considering four standalone machine-learning and statistical approaches, namely, Logistic Regression (LR), Shannon Entropy (SE), Weights-of-Evidence (WoE), and Frequency Ratio (FR) models. To this end, geohazard inventories were prepared using remote sensing techniques with field observations and historical hazard datasets. The spatial relationship of thirteen conditioning factors, namely, slope (degree), distance to faults, geology, elevation, distance to rivers, slope aspect, distance to road, annual mean rainfall, normalized difference vegetation index, profile curvature, stream power index, topographic wetness index, and land cover, with hazard distribution was analyzed. The results showed that faults, slope angles, elevation, lithology, land cover, and mean annual rainfall play a key role in controlling the spatial distribution of geohazards in the study area. The final susceptibility maps were validated against ground truth points and by plotting Area Under the Receiver Operating Characteristic (AUROC) curves. According to the AUROC curves, the success rates of the LR, WoE, FR, and SE models were 85.30%, 76.00, 74.60%, and 71.40%, and their prediction rates were 83.10%, 75.00%, 73.50%, and 70.10%, respectively; these values show higher performance of LR over the other three models. Furthermore, 11.19%, 9.24%, 10.18%, 39.14%, and 30.25% of the areas corresponded to classes of very-high, high, moderate, low, and very-low susceptibility, respectively. The developed geohazard susceptibility map can be used by relevant government officials for the smooth implementation of the CPEC project at the regional scale.

Effective texture feature is an essential component in any content based image retrieval system. In the past, spectral features, like Gabor and wavelet, have shown superior retrieval performance than many other statistical and structural based features. Recent researches on multi-resolution analysis have found that curvelet captures texture properties, like curves, lines, and edges, more accurately than Gabor filters. However, the texture feature extracted using curvelet transform is not rotation invariant. This can degrade its retrieval performance significantly, especially in cases where there are many similar images with different orientations. This paper analyses the curvelet transform and derives a useful approach to extract rotation invariant curvelet features. Experimental results show that the new rotation invariant curvelet feature outperforms the curvelet feature without rotation invariance.

This study investigates the utilization of waste iron slag (WIS) as a sustainable alternative in concrete production to reduce environmental impact and preserve natural resources. The experimental investigation of WIS-incorporated concrete focused on compressive and tensile strength with machine learning (ML) models for prediction. Among the tested ML algorithms, Decision Tree (DT) and XGBoost showed the highest accuracy (R² = 0.95135) in predicting concrete strength properties, while models like SVM and Symbolic Regression underperformed. Experimental results indicate that up to 20 % WIS replacement maintains adequate strength, whereas higher proportions reduce structural integrity. A ranking score index and cost analysis confirmed the technical and economic feasibility of using WIS in concrete. Cost analysis demonstrated substantial cost savings with 25 % WIS incorporation, confirming its economic feasibility. Integrating experimental data with ML predictions highlights WIS's potential for sustainable concrete applications, enabling optimized mix designs and reduced reliance on physical testing. Future work should address limitations, including dataset expansion and the exploration of additional durability and mechanical properties to validate WIS's practicality in construction further.

Dhaka city is experiencing rapid land cover changes, and the effects of climate change are highly visible. Investigating their combined influence on runoff patterns is vital for sustainable urban planning and water resources management. In this work, multi-date land cover classification was performed using a random forest (RF) algorithm. To validate accuracy of land cover classification, an assessment was conducted by employing kappa coefficient, which ranged from 85 to 96%, indicating a high agreement between classified images and the reference dataset. Future land cover changes were forecasted with cellular automata-artificial neural network (CA-ANN) model. Further, soil conservation service -curve number (SCS-CN) rainfall-runoff model combined with CMIP6 climate data was employed to assess how changes in land cover impact runoff within Dhaka metropolitan development plan (DMDP) area. Over the study period (2020–2100), substantial transformations of land cover were observed, i.e., built-up areas expanded to 1146.47 km² at the end of 2100, while agricultural areas and bare land diminished considerably. Consequently, monsoon runoff increased from 350.14 to 368.24 mm, indicating elevated hydrological responses. These findings emphasized an intricate interplay between urban dynamics and climatic shifts in shaping runoff patterns, underscoring urgency of incorporating these factors into urban planning strategies for sustainable water resources management in a rapidly growing city such as Dhaka.