Browsing by Author "Saurabh Kumar Singh"

Now showing 1 - 7 of 7

A Novel Multi-Layer Attention Boosted YOLOv10 Network for Landslide Mapping Using Remote Sensing Data
(John Wiley and Sons Inc, 2025) Naveen Chandra; Himadri Vaidya; Neelima D. Satyam; Xiaochuan Tang; Saurabh Kumar Singh; Sansar Raj Meena
Detecting landslides is a critical challenge within the remote sensing fraternity, especially given the need for timely and accurate hazard assessment. Traditional methods for identifying landslides from remote sensing data are often manual or partially automated; however, with the progress of computer vision technology, the automated methods based on deep learning algorithms have gained significant attention. Furthermore, attention mechanisms, inspired by human visual structure, have grown remarkably in various applications, including hazard studies. In this study, we leverage the capabilities of YOLO models, especially YOLOv10 and its variants, to automate the detection of landslides. We applied four prevailing attention mechanisms: CBAM, ECA, GAM, and SA. Models are trained using the Bijie landslide detection database. Moreover, the best results are unveiled based on the evaluation criteria, that is, precision, recall, f-score, and mAP. The YOLOv10m+CBAM showed the best performance with map@50-95 of 78.5%. Our results demonstrate a robust system capable of rapidly identifying and localizing landslide events with significant detection speed and accuracy improvements. This advancement augments the process of landslide detection and supports more effective disaster response and management. © 2025 The Author(s). Transactions in GIS published by John Wiley & Sons Ltd.
Interplay between anisotropy and magnetic exchange to modulate the magnetic relaxation behaviours of phenoxo bridged Dy2 dimers with axial β-diketonate co-ligands
(Royal Society of Chemistry, 2022) Soumalya Roy; Pooja Shukla; Naushad Ahmed; Ming-Hao Du; Ibtesham Tarannum; Xiang-Jian Kong; Tulika Gupta; Saurabh Kumar Singh; Sourav Das
A series of Schiff base LH ((E)-2-((pyridin-2-ylmethylene)amino)phenol) supported phenoxo bridged symmetric [Dy2(L)2(hfac)4] (1), [Dy2(L)2(tfac)4] (2) and asymmetric [Dy2(L)2(thd)3(NO3)]·1.5H2O (3) binuclear complexes were isolated using differently substituted β-diketonate co-ligands (Hhfac = hexafluoroacetylacetonate, Htfac = trifluoroacetylacetonate, and Hthd = 2,2,6,6-tetramethyl-3,5-heptanedione). In all the three complexes 1-3, the two LH ligands provide phenoxo bridging and N-donor atoms. The {Dy2(μ2-O)2} magnetic core structures with LH ligands are found to be the same in 1-3 while the dissimilar functionalities of the axially coordinated different β-diketonate co-ligands play a crucial role in modulating the magnetic anisotropy of individual DyIII sites and magnetic exchange between them. The experimental static magnetic behaviour suggests the presence of intramolecular antiferromagnetic interactions in all the three complexes 1-3. The strength of the magnetic exchange coupling decreases with increasing magnetic anisotropy of individual DyIII ions from complex 1 to complex 3 and simultaneously their zero-field slow magnetic relaxation behaviors were found to increase with effective energy barriers (ΔE/kB) of 9.04 K, 24.06 K and 25.65 K, respectively. Furthermore, the DFT and ab initio theoretical calculations performed on the X-ray structures of complexes 1-3 support our experimental findings. © 2022 The Royal Society of Chemistry.
Machine learning approach for detection of land subsidence induced by underground coal fire using multi-sensor satellite data
(Taylor and Francis Ltd., 2025) Ashwani Raju; Mansi Sinha; Saurabh Kumar Singh; Praveen Kumar Kannojiya; Mitali Sinha; Ramesh P. Singh
High-rank coal reserves in Jharia Coalfield (JCF, India), are invariably associated with underground coal fires and land subsidence. This study explores multi-sensor time series satellite data (Landsat 8 OLI and Sentinel-1) through machine learning (ML) to determine the regional ground deformation accompanying coal fires and their contextual relationship. The results show that the highest degree of subsidence is closely associated with the active mine benches with overburden dumps. The relationship between the coal fire and land subsidence parameters is considered as a binary classification problem, explored by calculating the probability of subsidence with a desirable categorical outcome through different ML models. The accuracy of the models is validated using performance metrics that shows that the Random Forest (RF) metrics predict the probability of deformation locations in response to the volume reduction of the burning coal fire and vertical compression due to Overburden Dump (OBD) near active mine benches. The estimated displacement trends have been used to forecast the Autoregressive Integrated Moving Average (ARIMA) method, estimated using Line-of-Sight (LOS) displacement values vary around the best fit within the 95% confidence limits. The trend shows ∼15–25% increase in subsidence compared to the cumulative subsidence. © 2024 Informa UK Limited, trading as Taylor & Francis Group.
Metamorphic evolution of sapphirine- and sodicgedrite-anorthite-bearing granulites, Rampur domain, Eastern Ghats Province, India
(Cambridge University Press, 2025) Rajeev Kumar Pandey; Divya Prakash; Saurabh Kumar Singh; Bikash Mahanta; Chandrakant Singh; Kamesh Sharma; Manish Kumar; Mahendra Kumar Singh
The Eastern Ghats Belt (EGB) has been extensively studied by the geoscientific community; however, this communication reports unique mineral assemblages that have not been documented previously. This study documents the occurrence of sapphirine, spinel, orthopyroxene, sodic-gedrite, calcic-amphibole, biotite and plagioclase assemblage indicating in ultrahigh temperature (UHT) metamorphic conditions. The significance of this study lies in the peculiarity of sapphirine being present within anorthite matrix which has been reported for the first time from the Indian subcontinent. The studied assemblage has been correlated with the more or less similar assemblage of rock called 'Sakenites' reported from southern Madagascar to correlate the most probable source rock 'anorthosites' that underwent metamorphic transformations and led to the unique UHT mineral assemblage. The Na-rich gedrite identified within the assemblage represents a relict mineral indicative of high-grade amphibolite-facies metamorphism. The derived pressure-temperature (P-T) trajectory reveals a decompression path with almost uniformly decreasing P-T conditions in contrast to the commonly reported isothermal decompression (ITD) path from various other domains and provinces of the EGB. The corresponding retrograde assemblage has been recalibrated by the sequential removal of sapphirine and corroborated with T-X (H2O) constraints. The analyzed EMP U-Th-Pb monazite chemical age constraints suggest mesoproterozoic to neoproterozoic episodes corresponding to a pair of ∼959 Ma and ∼846 Ma thermal events. These metamorphic events have been correlated to reconstructing the Rodinian supercontinent at ∼959 Ma and the initiation of its subsequent break-up at ∼846 Ma. © The Author(s), 2025. Published by Cambridge University Press.
Optimized YOLOv8 with multi-level attention for satellite image-based landslide detection
(Elsevier Ltd, 2025) Naveen Chandra; Himadri Vaidya; Magaly Koch; Rajeshwari Bhookya; Saurabh Kumar Singh; Sansar Raj Meena
Detecting landslide events presents a significant challenge in remote sensing, especially as computer vision technologies continue to advance. Landslide detection from remotely sensed images has traditionally relied on manual or semi-automated processes. However, with the rapid development of computational resources, there has been a shift towards automatic methods leveraging deep learning algorithms. Moreover, attention models, inspired by the human visual system, have emerged substantially providing improved solutions for object detection-related problems especially, landslide mapping. Therefore, this research work introduces an enhanced YOLOv8 (nano (n), small (s), and medium (m)) network incorporating popular attention modules, specifically convolutional block attention module (CBAM), efficient channel attention (ECA), and shuffle attention (SA), for enhancing landslide detection accuracy using satellite images. The original YOLOv8 is improved by adding the attention layer discretely after the C2F module within the neck. The addition of an attention layer enables the model to concentrate on the most informative parts of the feature maps combining the capabilities of both channel and spatial attention mechanisms for detecting subtle landslide features. The experiments are conducted using the publicly available Bijie landslide detection database. Standard evaluation metrics, including precision, recall, F-score, and mean average precision (mAP), are used for quantitative analysis. Among the variants tested, YOLOv8n + ResCBAM demonstrates the most promising performance. This study underscores the model's efficacy in facilitating inventory preparation and precise landslide mapping for disaster recovery and response efforts, thereby supporting early prediction models. © 2025
Phase equilibria modelling, fluid inclusion study, and U-Pb zircon dating of ultra-high temperature mafic granulites from Rampur domain, Eastern Ghats province: implications for the Indo-Antarctic correlation
(Springer Science and Business Media Deutschland GmbH, 2025) Divya Prakash; Rajeev Kumar Pandey; Saurabh Kumar Singh; Chandrakant Singh; Manish Kumar; Bikash Mahanta; Aditya Kharya; Himanshu Kumar Sachan; Kamesh Sharma
The study area (Rampur domain) is situated to the east of the Eastern Ghats Boundary Shear Zone (EGBSZ) and encompasses portions of the granulite facies rocks of the exhumed Proterozoic Eastern Ghats Province (EGP), India. The EGP is characterized by a diverse array of rock types, featuring a wide variety of mineral parageneses and chemical compositions, including charnockite, mafic granulite, Mg-Al granulite, felsic granulites, amphibolite, khondalite and anorthosite. In this study, we report for the first time evidence of ultra-high temperature (UHT) metamorphism within the mafic granulites of the relatively unexplored Rampur domain of the Eastern Ghats Province, using the two-pyroxene assemblage. The stable mineral assemblage present during peak metamorphism typically includes garnet, orthopyroxene1, clinopyroxene, hornblende1, quartz, and plagioclase1. The consumption of garnet observed in different reaction textures, alongside the formation of striking orthopyroxene2–plagioclase2 and hornblende2–plagioclase2 symplectites, represent the later phases of metamorphism. By applying TWQ calculation procedures to the mineral core compositions, we have determined peak metamorphic conditions of approximately 970 °C at a pressure of 10.5 kbar. Zircon dating results from LA-HR-ICP-MS indicate upper intercept ages of 2509.9 ± 21.7 Ma and 2479.9 ± 21.0 Ma for the protolith, while lower intercept ages of 965.7 ± 40.7 Ma and 979.8 ± 18.1 Ma correspond to the metamorphic age of the analyzed samples E-185 and E-186, respectively. Based on the textural relationship, derived zircon ages, fluid-P-T constraints, and P-T pseudosection model, we propose a decompressional evolutionary P-T-t path that supports the Neo-Proterozoic assembly of the Indo-Antarctic region. © The Author(s), under exclusive licence to Springer-Verlag GmbH Germany, part of Springer Nature 2025.
Ultrahigh-temperature granulites from the Shillong-Meghalaya Gneissic Complex, NE India: Implications for the Indo-Antarctic Correlation
(Elsevier Ltd, 2025) Bikash Mahanta; Divya Prakash; Manish Kumar; Saurabh Kumar Singh; Rajeev Kumar Pandey; Chandrakant Singh; Roopali Yadav; Jesus Solé Vinas
The Shillong-Meghalaya Gneissic Complex (SMGC) in the Riangdo region, northeastern India, is mainly composed of metamorphic rocks from upper amphibolite to ultrahigh temperature (UHT) granulite facies with several igneous intrusions. The pelitic granulite comprises biotite, garnet, K-feldspar, sillimanite, spinel, quartz, and biotite. This study is the first to report ultrahigh-temperature (UHT) metamorphism in the Riangdo (Sonapahar) block of the SMGC. Metamorphic pressure–temperature conditions estimated from the Spinel + Quartz bearing pelitic granulite using conventional thermobarometer (THERMOCALC) and pseudosection modelling in the MnO-Na2O–CaO–K2O–FeO–MgO–Al2O3–SiO2–H2O–TiO2–Fe2O3 system are more than 900 °C and pressure of about 8 kbars, representing UHT metamorphism. The sequence of reactions, constructed from the post-peak textural relationship, along with petrogenetic grid and pseudosection modelling, records a clockwise P–T evolution. This indicates an isothermal decompression path associated with rapid uplift before cooling of the tectonically thickened crust. Available geochronological ages suggest the presence of widespread Pan-African tectonothermal events in the SMGC. The K-Ar isotopic ages obtained from biotite suggest a cooling age of 407.20 ± 3.49 Ma. Given the general acceptance of UHT with clockwise isothermal decompression in Pan-African age metamorphism in the East-African-Antarctic Orogen (EAAO) and Eastern Ghat Mobile Belt (EGMB), the Sonapahar UHT metamorphic history is considered to be part of this record. © 2024 Elsevier Ltd