Machine learning-based estimation of land surface temperature variability over a large region: a temporally consistent approach using single-day satellite imagery.

Accurate retrieval of LST is crucial for understanding and mitigating the effects of urban heat islands, and ultimately addressing the broader challenge of global warming. This study emphasizes the importance of a single day satellite imageries for large-scale LST retrieval. It explores the impact of Spectral indices of the surface parameters, using machine learning algorithms to enhance accuracy. The research proposes a novel approach of capturing satellite data on a single day to reduce uncertainties in LST estimations. A case study over Chandigarh city using Extreme Gradient Boosting (XGBoost), Light Gradient Boosting Machine, and Random Forest (RF) reveals RF's superior performance in LST estimations during both summer and winter seasons. All the ML models gave an R-square of above 0.8 and RF with slightly higher R-square during both summer (0.93) and winter (0.85). Building on these findings, the study extends its focus to Ranchi, demonstrating RF's robustness with impressive accuracy in capturing LST variations. The research contributes to bridging existing gaps in large-scale LST estimation methodologies, offering valuable insights for its diverse applications in understanding Earth's dynamic systems.

Generation and classification of patch-based land use and land cover dataset in diverse Indian landscapes: a comparative study of machine learning and deep learning models.

In the context of environmental and social applications, the analysis of land use and land cover (LULC) holds immense significance. The growing accessibility of remote sensing (RS) data has led to the development of LULC benchmark datasets, especially pivotal for intricate image classification tasks. This study addresses the scarcity of such benchmark datasets across diverse settings, with a particular focus on the distinctive landscape of India. The study entails the creation of patch-based datasets, consisting of 4000 labelled images spanning four distinct LULC classes derived from Sentinel-2 satellite imagery. For the subsequent classification task, three traditional machine learning (ML) models and three convolutional neural networks (CNNs) were employed. Despite facing several challenges throughout the process of dataset generation and subsequent classification, the CNN models consistently attained an overall accuracy of 90% or more. Notably, one of the ML models stood out with 96% accuracy, surpassing CNNs in this specific context. The study also conducts a comparative analysis of ML models on existing benchmark datasets, revealing higher prediction accuracy when dealing with fewer LULC classes. Thus, the selection of an appropriate model hinges on the given task, available resources, and the necessary trade-offs between performance and efficiency, particularly crucial in resource-constrained settings. The standardized benchmark dataset contributes valuable insights into the relative performance of deep CNN and ML models in LULC classification, providing a comprehensive understanding of their strengths and weaknesses.

Machine learning-based digital mapping of soil organic carbon and texture in the mid-Himalayan terrain.

Mountain soils have received significant attention due to their profound influence on ecological processes and environmental factors. However, mapping these soils in digital soil mapping technique encounters several challenges, including high local variability, non-linear relationships between environmental covariates and soil properties, limited accessibility in complex topographical settings, and the absence of universally applicable covariates for soil formation. To address these issues, this study integrates soil-forming factors of the scorpan model to map soil organic carbon (SOC) and soil texture in the mid-Himalayas. By considering over 100 environmental covariates, with a focus on terrain parameters relevant to mountainous environments, the study aims to enhance the accuracy of ML regression models through augmentation techniques that overcome data insufficiency. Using augmented soil observations and covariates, a non-parametric random forest regression model is trained and applied to predict soil variables across the study area, generating a continuous fine-resolution map. The model's performance, evaluated against an unknown dataset, was significant with an R-square of 0.80, 0.79, 0.72, and 0.84 for clay, sand, silt, and SOC, respectively. Furthermore, a sensitivity analysis of the environmental covariates and their impact on the model revealed that all the soil-forming factors make a significant contribution to the model's effectiveness. The insights gained from this research contribute to a better understanding of mountain soils and facilitate the development of effective conservation and sustainable management strategies for mountainous regions.

Implication of rare genetic variants of NODAL and ACVR1B in congenital heart disease patients from Indian population.

NODAL signaling plays an essential role in vertebrate embryonic patterning and heart development. Accumulating evidences suggest that genetic mutations in TGF-ß/NODAL signaling pathway can cause congenital heart disease in humans. To investigate the implication of NODAL signaling in isolated cardiovascular malformation, we have screened 300 non-syndromic CHD cases and 200 controls for NODAL and ACVR1B by Sanger sequencing and identified two rare missense (c.152C > T; p.P51L and c.981 T > A; p.D327E) variants in NODAL and a novel missense variant c.1035G > A; p.M345I in ACVR1B. All these variants are absent in 200 controls. Three-dimensional protein-modelling demonstrates that both p.P51L and p.D327E variations of NODAL and p.M345I mutation of ACVR1B, affect the tertiary structure of respective proteins. Variants of NODAL (p.P51L and p.D327E) and ACVR1B (p.M345I), significantly reduce the transactivation of AR3-Luc, (CAGA)12-Luc and (SBE)4-Luc promoters. Moreover, qRT-PCR results have also deciphered a reduction in the expression of cardiac-enriched transcription factors namely Gata4, Nkx2-5, and Tbx5 in both the mutants of NODAL. Decreased expression of, Gata4, Nkx2-5, Tbx5, and lefty is observed in p.M345I mutant of ACVR1B as well. Additionally, reduced phosphorylation of SMAD2/3 in response to these variants, suggests impaired NODAL signaling and possibly responsible for defective cell fate decision and differentiation of cardiomyocytes leading to CHD phenotype.

A gain-of-function mutation in CITED2 is associated with congenital heart disease.

CITED2 is a transcription co-activator that interacts with TFAP2 and CBP/ P300 transcription factors to regulate the proliferation and differentiation of the cardiac progenitor cells. It acts upstream to NODAL-PITX2 pathways and regulates the left-right asymmetry. Both human genetic and model organism studies have shown that altered expression of CITED2 causes various forms of congenital heart disease. Therefore, we sought to screen the coding region of CITED2 to identify rare genetic variants and assess their impact on the structure and function of the protein. Here, we have screened 271 non-syndromic, sporadic CHD cases by Sanger's sequencing method and detected a non-synonymous variant (c.301C>T, p.P101S) and two synonymous variants (c.21C>A, p.A7A; c.627C>G, p.P209P). The non-synonymous variant c.301C>T (rs201639244) is a rare variant with a minor allele frequency of 0.00011 in the gnomAD browser and 0.0018 in the present study. in vitro analysis has demonstrated that p.P101S mutation upregulates the expression of downstream target genes Gata4, Mef2c, Nfatc1&2, Nodal, Pitx2, and Tbx5 in P19 cells. Luciferase reporter assay also demonstrates enhanced activation of downstream target promoters. Further, in silico analyses implicate that increased activity of mutant CITED2 is possibly due to phosphorylation of Serine residue by proline-directed kinases. Homology modeling and alignment analysis have also depicted differences in hydrogen bonding and tertiary structures of wild-type versus mutant protein. The impact of synonymous variations on the mRNA structure of CITED2has been analyzed by Mfold and relative codon bias calculations. Mfold results have revealed that both the synonymous variants can alter the mRNA structure and stability. Relative codon usage analysis has suggested that the rate of translation is attenuated due to these variations. Altogether, our results from genetic screening as well as in vitro and in silico studies support a possible role of nonsynonymous and synonymous mutations in CITED2contributing to pathogenesis of CHD.

Randomized crossover comparison of the laryngeal mask airway classic with i-gel laryngeal mask airway in the management of difficult airway in post burn neck contracture patients.

PURPOSE: The objective of the study was to compare the performance of i-gel supraglottic airway with cLMA in difficult airway management in post burn neck contracture patients and assess the feasibility of i-gel use for emergency airway management in difficult airway situation with reduced neck movement and limited mouth opening. METHODS: Prospective, crossover, randomized controlled trial was performed amongst forty eight post burn neck contracture patients with limited mouth opening and neck movement. i-gel and cLMA were placed in random order in each patient. Primary outcome was overall success rate. Other measurements were time to successful ventilation, airway leak pressure, fiberoptic glottic view, visualization of square wave pattern. RESULTS: Success rate for the i-gel was 91.7% versus 79.2% for the cLMA. i-gel required shorter insertion time (19.3 seconds vs. 23.5 seconds, P=0.000). Airway leak pressure difference was statistically significant (i-gel 21.2 cm H20; cLMA 16.9 cm H(2)0; P=0.00). Fiberoptic view through the i-gel showed there were less epiglottic downfolding and better fiberoptic view of the glottis than cLMA. Overall agreement in insertion outcome for i-gel was 22/24 (91.7%) successes and 2/24(8.3%) failure and for cLMA, 19/24 (79.16%) successes and 5/24 (16.7%) failure in the first attempt. CONCLUSION: The i-gel is cheap, effective airway device which is easier to insert and has better clinical performance in the difficult airway management of the airway in the post burn contracture of the neck. Our study shows that i-gel is feasible for emergency airway management in difficult airway situation with reduced neck movement and limited mouth opening in post burn neck.