28 July 2025 in The International Archives of the Photogrammetry, Remote Sensing and Spatial Information Sciences
An updated map of the area's land use land cover (LULC) is necessary for strategic planning and management of land use to shape the town sustainably. The advances in remote sensing imageries and artificial intelligence have facilitated the extraction of LULC classification. With the high number of studies on LULC mapping using various machine learning (ML) and deep learning (DL) algorithms incorporating imageries, no established algorithm shows stable results for all the datasets and study regions. Therefore, we used three robust machine learning algorithms, Random Forest (RF), Support Vector Machine (SVM), K-Nearest Neighbour (KNN), and four deep learning algorithms, Residual Network (ResNet50 and ResNet152) and Visual Geometry Group (VGG16 and VGG19), to understand which model can produce a highly accurate LULC map in the Indian context, which are inherently unplanned and unorganized using Sentinel 2 imageries. The results of these models were then comparatively analyzed statistically using Accuracy, Recall, Precision, F1-score, and Kappa coefficient. Although DL models require a large number of training datasets, they outperformed the ML algorithms with higher Kappa coefficient values (ResNET50 = 0.90, ResNET-152 = 0.91, VGG-16 = 0.94, VGG-19 = 0.94). VGG-19 has consistently given better performance in all accuracy metrics. Overall the study highlights the potential of deep learning models, particularly VGG-19, in generating highly accurate LULC maps for complex and unplanned urban environments in India. These findings underscore the importance of leveraging advanced AI techniques in remote sensing for effective land use planning and sustainable urban development.
28 July 2025 in The International Archives of the Photogrammetry, Remote Sensing and Spatial Information Sciences
Cement is a primary binding material that plays a crucial role in construction. This study used hyperspectral reflectance analysis to investigate the spectral reflectance characteristics of White Portland Cement (WPC) exposed to environmental conditions. The observation was made over a 150-day period. The reflectance of cement samples was measured using a spectroradiometer that captures the reflectance value of 994 discrete wavelength range from 339.3 nm to 2516.8 nm. These data were processed to calculate differential and double differential curves. Statistical techniques like moving average and smooth spline interpolation were employed to remove local fluctuations and observe the changing trends in reflectance over time. The study results provide insight into the temporal changes in the surface properties of WPC. The analysis also revealed significant changes in reflectance over time. The mean reflectance decreased from 90.397 on Day 0 to 83.092 on Day 150, showing surface degradation with time. However, the standard deviation of the reflectance increased initially from 7.318 on Day 0 to 7.766 on Day 30, then stabilized at 6.763 by Day 120. It was further increased to 7.496 by Day 150. The differential and double differential curves also show significant variations. The differential reflectance attained its maximum value of 0.199 on Day 60, and the double differential reflected maximum changes at 0.031 on Day 60. These results highlight the dynamic interaction between WPC surfaces and various environmental factors. The observed decrease in reflectance over time suggests surface ageing and potential material degradation, as reduced reflectance may indicate increased porosity or surface roughness due to environmental exposure. Overall, this study can offer a valuable tool for assessing cement-based materials' long-term durability and performance in the construction industry.
12 July 2025 in ISPRS Annals of the Photogrammetry, Remote Sensing and Spatial Information Sciences
Accurate land cover classification in riverine environments is essential for understanding hydrological dynamics, ecological health, and resource management. This study utilizes high-resolution LISS-4 imagery from the IRS-R2 satellite to address the complex classification challenges in the dynamic confluence of the Mahanadi and Shivnath Rivers. To enhance classification accuracy, two distinct feature sets were developed: the first feature set (FS-1) contained the original three spectral bands of the imagery, and the second feature set (FS-2) added eight derived spectral indices to improve class separation. Three machine learning classifiers, Random Forest (RF), Support Vector Machine (SVM), and Gradient Tree Boosting (GTB), were applied to assess the effectiveness of each feature set. The results demonstrated that the combination of FS-2 and RF yielded the most accurate and interpretable classification, achieving an overall accuracy of 84.48% and a Cohen’s Kappa coefficient of 0.81. Visual results demonstrated precise delineation of narrow water channels and sandbars, when using the enhanced feature set FS-2 with the Random Forest (RF) classifier, the model achieved an F1-score of 86.96% for dense vegetation and 83.78% for water. FS-2 consistently improved F1-scores across all classifiers, aiding in distinguishing visually similar classes like wet sand, dry sand, and sparse vegetation. These findings highlight the value of combining spectral indices with high-resolution imagery to achieve accurate land cover classification in complex landscapes, supporting applications in ecological monitoring, flood risk assessment, and resource management for riverine ecosystems.
28 July 2025 in The International Archives of the Photogrammetry, Remote Sensing and Spatial Information Sciences
Cement mortar is a fundamental material in construction, with its strength and durability influenced by mix proportions and curing conditions. This study investigates the spectral characteristics and compressive strength of cement mortar mixes with varying cement-to-sand ratios (1:3, 1:4, and 1:6) over curing periods of 7 and 14 days. Utilising an SVC HR-1024i field spectroradiometer, spectral reflectance measurements were conducted to assess the surface properties of mortar cubes, while compressive strength tests were performed using a Universal Testing Machine. Results demonstrate a strong correlation between mix composition, curing duration, and both reflectance and strength developed with time. Higher cement content resulted in increased compressive strength and reflectance, particularly on the top surfaces of the samples. Further, spectral reflectance values increased with curing time. It may indicate the influence of hydration and microstructural densification on surface characteristics. Overall, this research introduces spectral analysis as a non-destructive method for evaluating mortar quality. It also offers a practical alternative to hectic and time-consuming traditional strength testing approaches. By highlighting the significant differences in reflectance based on mix proportions and curing conditions, the findings can contribute to improved quality control in construction materials. It can promote further exploration of non-destructive testing methodologies in this field.