This study aims to evaluate the air quality of the Haryana state, India by utilizing Sentinel-5P satellite data. This study aims to track, quantify, and analyze the level of air pollutants in several regions of Haryana. By integrating and analyzing diverse satellite datasets, the study provides a comprehensive understanding of air quality conditions in the region and supports informed decision-making for pollution mitigation and environmental sustainability. This also examines the public health and environmental impacts of air pollution, identifies pollution sources, reviews existing policies, and also provides recommendations for prevention of air pollution. The outcomes of this study will improve the understanding of air quality dynamics in Haryana and provide preventive measures towards sustainable environmental practices. This paper presents a detailed assessment of air quality in Haryana, India, covering the period from 2019 to 2023 using satellite datasets. This evaluates the concentrations and spatial distributions of air pollutants across Haryana. The experimental results provide significant variations in pollution levels over the four years, with higher concentrations in 2019 and 2021, and lower levels in 2020 and 2023. Moreover, spatial distribution maps illustrate pollutant patterns, emphasizing the temporal and spatial changes in pollution levels. The results also highlight the ongoing challenge of increasing pollution in certain areas of Haryana and the need for continuous monitoring to improve air quality.

Uttarakhand is one of the most landslide-susceptible states because of its geographical setting, which consists of 86% of the Himalayan terrain. However, in recent years, landslides have increased dramatically due to the large number of settlements, farms, road buildings, and a wide variety of hydroelectric projects. Therefore, this is a need to study the landslides scrupulously at a regional scale to rein the future developmental planning models. In the current work, a comprehensive study has been undertaken for the assessment of landslide susceptibility zones using the weight of evidence (WOE) and risk assessment for the Tehri region, specifically around the Tehri reservoir. Landslides are derived through remotesensing techniques and other sources such as slope, geology, aspect, geomorphology, land use/land cover, drainage, lineaments, and more. After that, the WOE method is applied to integrate causative factors for the mapping of susceptible landslide zones, where the weights have been assigned to each layer according to available literatures. Subsequently, vulnerability is prepared for the area by integrating layers through the weighted sum technique. Finally, a risk map was prepared by integrating a susceptibility and vulnerability map. All three maps, namely, vulnerability, landslide susceptibility, and risk maps, were classified into five zones: very low, low, moderate, high, and very high. The results obtained from final maps and plots indicate that approximately 8% of the area is in a high susceptible zone, 50% is in a moderate susceptible zone, 54% is in a very low-risk zone, 23% is in a moderaterisk zone, and 14% is in a very high-risk zone. This study identified and illustrated the causative factors, combined into a GIS environment to identify landslide-prone locations. Then, depending upon the potency of an element, suitable and effective preventive measures may be taken to reduce the impact of the disaster. The concerned government agencies can use the same map while mapping disaster management, developing future strategies, implementing rehabilitation programs, and environmental planning.

This paper proposes a gradient-based data fusion and classification approach for Synthetic Aperture Radar (SAR) and optical image. This method is used to intuitively reflect the boundaries and edges of land cover classes present in the dataset. For the fusion of SAR and optical images, Sentinel 1A and Sentinel 2B data covering Central State Farm in Hissar (India) was used. The major agricultural crops grown in this area include paddy, maize, cotton, and pulses during kharif (summer) and wheat, sugarcane, mustard, gram, and peas during rabi (winter) seasons. The gradient method using a Sobel operator and color components for three directions (i.e., x, y, and z) are used for image fusion. To judge the quality of fused image, several fusion metrics are calculated. After obtaining the resultant fused image, gradient based classification methods, including Stochastic Gradient Descent Classifier, Stochastic Gradient Boosting Classifier, and Extreme Gradient Boosting Classifier, are used for the final classification. The classification accuracy is represented using overall classification accuracy and kappa value. A comparison of classification results indicates a better performance by the Extreme Gradient Boosting Classifier.

Farmers face a number of difficulties on a daily basis, including the inability to document farm input costs, farm chemical expenditures, and statistics on farm output, as well as obtain information from other stakeholders (such as agriculture advisers). Farmers’ findings are gathered via a crowdsourcing strategy; the project is run through a smartphone application called ClimMob, which combines and analyzes decentralized field data from multiple growers. As more non-governmental groups and national agricultural research organizations use the online platform for their own initiatives, ClimMob is starting to take on a life of its own. When it comes to data accessibility, agricultural growth in remote places, and other factors, we come to the conclusion that mobile crowdsourcing (MCS) applications are highly valued in strengthening these areas.

The NH 58 area in India has been experiencing an increase in landslide occurrences, posing significant threats to local communities, infrastructure, and the environment. The growing need to identify areas prone to landslides for effective disaster risk management, land use planning, and infrastructure development has led to the increased adoption of advanced geospatial technologies and statistical methods. In this context, this research article presents an in-depth analysis aimed at developing a landslide susceptibility zonation (LSZ) map for the NH 58 area using remote sensing, GIS, and logistic regression analysis. The study incorporates multiple geo-environmental factors for analysis, such as slope aspect, curvature, drainage density, elevation, fault distance, flow accumulation, geology, geomorphology, land use land cover (LULC), road distance, and slope angle. Utilizing 50% of the landslide inventory data, the logistic regression model was trained to determine correlations between causal factors and landslide occurrences. The logistic regression model was then employed to calculate landslide probabilities for each mapping unit within the NH 58 area, which were subsequently classified into relative susceptibility zones using a statistical class break technique. The model’s accuracy was verified through ROC curve analysis, resulting in a 92% accuracy rate. The LSZ map highlights areas near road cut slopes as highly susceptible to landslides, providing crucial information for land use planning and management to reduce landslide risk in the NH 58 area. The study’s findings are beneficial for policymakers, planners, and other stakeholders involved in regional disaster risk management. This research offers a comprehensive analysis of landslide-influencing factors in the NH 58 area and introduces an LSZ map as a valuable tool for managing and mitigating landslide risks. The map also serves as a critical reference for future research and contributes to the broader understanding of landslide susceptibility in the region.

The process of classifying images involves grouping pixels with similar characteristics into one class or cluster. Traditional pixel-based classification methods such as support vector machine, random forest, and decision tree yield poor results for synthetic aperture radar imagery (SAR) because of limited spectral information. This chapter provides the results of a two-dimensional (2D)-convolutional neural network (CNN)-based classification using Sentinel-1 (SAR) data over the Central State Farm, Hissar, Haryana, India. Hyperparameters of 2D-CNN were optimized using Bayesian optimization. Several textural features derived from S1 data were also layer-stacked with both vertical–vertical (VV) and vertical–horizontal (VH) polarized images. Results suggest that using texture features obtained from both VV and VH images improved classification accuracy for the considered area.

Remote sensing image classification is difficult, especially for agricultural crops with identical phenological growth periods. In this context, multi-sensor image fusion allows a comprehensive representation of biophysical and structural information. Recently, Convolutional Neural Network (CNN)-based methods are used for several applications due to their spatial-spectral interpretability. Hence, this study explores the potential of fused multi-temporal Sentinel 1 (S1) and Sentinel 2 (S2) images for Land Use/Land Cover classification over an agricultural area in India. For classification, Bayesian optimised 2D CNN-based DL and pixel-based SVM classifiers were used. For fusion, a CNN-based siamese network with Ratio-of-Laplacian pyramid method was used for the images acquired over the entire winter cropping period. This fusion strategy leads to better interpretability of results and also found that 2D CNN-based DL classifier performed well in terms of classification accuracy for both single-month (95.14% and 96.11%) as well as multi-temporal (99.87% and 99.91%) fusion in comparison to the SVM with classification accuracy for single-month (80.02% and 81.36%) and multi-temporal fusion (95.69% and 95.84%). Results indicate better performance by Vertical-Vertical polarised fused images than Vertical-Horizontal polarised fused images. Thus, implying the need to analyse classified images obtained by DL classifiers along with the classification accuracy.

This work quantifies the impact of pre-, during- and post-lockdown periods of 2020 and 2019 imposed due to COVID-19, with regards to a set of satellite-based environmental parameters (greenness using Normalized Difference Vegetation and water indices, land surface temperature, night-time light, and energy consumption) in five alpha cities (Kuala Lumpur, Mexico, greater Mumbai, Sao Paulo, Toronto). We have inferenced our results with an extensive questionnaire-based survey of expert opinions about the environment-related UN Sustainable Development Goals (SDGs). Results showed considerable variation due to the lockdown on environment-related SDGs. The growth in the urban environmental variables during lockdown phase 2020 relative to a similar period in 2019 varied from 13.92% for Toronto to 13.76% for greater Mumbai to 21.55% for Kuala Lumpur; it dropped to -10.56% for Mexico and -1.23% for Sao Paulo city. The total lockdown was more effective in revitalizing the urban environment than partial lockdown. Our results also indicated that Greater Mumbai and Toronto, which were under a total lockdown, had observed positive influence on cumulative urban environment. While in other cities (Mexico City, Sao Paulo) where partial lockdown was implemented, cumulative lockdown effects were found to be in deficit for a similar period in 2019, mainly due to partial restrictions on transportation and shopping activities. The only exception was Kuala Lumpur which observed surplus growth while having partial lockdown because the restrictions were only partial during the festival of Ramadan. Cumulatively, COVID-19 lockdown has contributed significantly towards actions to reduce degradation of natural habitat (fulfilling SDG-15, target 15.5), increment in available water content in Sao Paulo urban area(SDG-6, target 6.6), reduction in NTL resulting in reducied per capita energy consumption (SDG-13, target 13.3).

SAR and optical data are widely used in image fusion to provide the complimentary information of each other and obtain the spatial and spectral features for improved classifications. This paper proposes to use multi-temporal data form Sentinel-1 (VV & VH polarization) and Sentinel-2 sensors for the fusion and classification over an agricultural area. Convolutional Neural Network (CNN)- based Pyramid method for fusion and Bayesian Optimized 2-D CNN for classification of fused multi-temporal data was used to extract spatial-spectral information. Results in terms of classification accuracy suggests slightly better performance by VV polarized fused images than the VH and also suggests an improved performance by multi-temporal data in comparison to the single date data over the study area.

Recently, deep learning (DL) techniques including Convolutional neural network (CNN), Recurrent neural network (RNN), and Recurrent-Convolutional neural network (R-CNN) have been extensively used to classify the remotely sensed data. Out of various deep learning algorithms, CNN-based algorithms are most widely used for the satellite image classification. Despite the improved performance of CNN, it also requires various hyper-parameters for training the network architecture to achieve the desired classification accuracy. Keeping in view the fact that the accuracy achieved by any classification algorithms is influenced by a suitable choice and value of hyper-parameter, this paper discusses the influence of several hyper-parameters on the classification accuracy of CNN classifier using three remote sensing datasets. The aim of this study is not to propose a set of values of different hyper-parameters but to study their influence on land cover classification accuracy with remote sensing datasets. Experimental results from the study indicate that various hyper-parameters affect the performance of CNN classifier to different extent suggesting a need to select the optimal value of these hyper-parameters for land cover classification studies using considered datasets.

LULC mapping is essential for any satellite data to visualize the land information. This study aims to focus on the performance evaluation of Machine Learning (ML) Algorithms for LULC mapping of satellite datasets. Optical (Sentinel-2), Microwave (Sentinel-1), and fused datasets have been generated using Ehlers, Brovey and Principal Component fusion. For each dataset, two ML Algorithms i.e. Random Forest (RF) and Support Vector Machine (SVM) have been applied. Results suggested that the optical and fused dataset achieved the more promising results than the microwave dataset as it contains only the backscatter information. Moreover, fusion of microwave with optical achieved more realistic LULC classification results. The overall accuracy derived for optical, microwave, and fused data are 92 %, 93.43 %, 37.71 %, 37.14 %, 85.71 % and 89.14 % using RF and SVM classifiers, respectively.

Image fusion combines the images of different spectral, spatial, multi-date, as well as radiometric data to achieve a better quality image for improved classification results. Recently, Convolution Neural Network (CNN)-based classification algorithms are extensively used for remote sensing applications. Keeping this in view, present work proposes to use CNN-based fusion and classification of Sentinel 1 (VV and VH polarization) and Sentinel 2 datasets acquired over an agricultural area near Hisar (India). For image fusion, three CNN-based approaches are used to fuse Sentinel 2 (10 m) data with VV and VH bands of Sentinel 1 data. After fusion, classification was performed using 2D-CNN classifier to judge the performance of fused images in terms of classification accuracy. Results suggest that out of the three fusion approaches, only infrared image fusion (IVF) approach performed well with the considered dataset in terms of fusion indicators and classification accuracy. Keeping in view of its better performance, this study proposes a modified IVF approach by using different image pyramid methods. Comparison of results suggests an improved performance by modified IVF approach for the fusion of Sentinel 2 and Sentinel 1 data in comparison with the original IVF approach.

Floods are investigated to be the utmost frequent and destructive phenomena among all other types of natural calamities worldwide. Thus, flood events need to be mapped to understand their impact on the affected region. The present case study is intended to examine and analyze the flood events occurred in July-August 2019 over the Northern Bihar region situated in Kosi and Gandak river basins. Furthermore, a comparative study was carried out to map the satellite based near real time flood inundation using multi-temporal Sentinel-1A (SAR) and MODIS NRT Flood data (optical and 3-day composite). Optical (MODIS) and Sentinel-1 SAR data were acquired to compare their flood inundation extent and the result shows overestimation in MODIS flood data due to varying spatial resolutions.

SAR (VV and VH polarization) and optical data are widely used in image fusion to use the complimentary information of each other and to obtain the better-quality image (in terms of spatial and spectral features) for the improved classification results. The optical data acquisition depends on whether conditions while SAR data can acquire the data in presence of clouds. This paper uses anisotropic diffusion with PCA for the fusion of SAR (Sentinel 1 (S1)) and Optical (Sentinel 2 (S2)) data for patch-based SVM Classification with LBP (LBP-PSVM). Fusion results with VV polarization performed better than VH polarization using considered fusion method. Classification results suggests that the LBP-PSVM classifier is more effective in comparison to SVM and PSVM classifiers for considered data.

The classification accuracy and the computational complexity are degraded by the occurrence of nonlinear data and mixed pixels present in satellite images. Therefore, the kernel-based fuzzy classifiers are required for the separation of linear and nonlinear data. This paper presents two classifiers for handling the nonlinear separable data and mixed pixels. The classifiers, noise clustering (NC) and NC with hypertangent kernels (NCH), are used for handling these problems in the satellite images. In this study, a comparative study between NC and NCH has been carried out. The membership values of KFCM are obtained to produce the final result. It is found that the proposed classifiers achieved good accuracy. It is observed that there is an enhancement in the classification accuracy by using NC and NCH. The maximum accuracy achieved for NC and NCH is 75% at δ = 0.7, δ = 0.5, respectively. After comparing both the results, it has identified that NCH gives better results. The classification of Formosat-2 data is done by obtaining optimized values of m and δ to generate the fractional outputs. The classification accuracy is performed by using the error matrix with the incorporation of hard classifier and α-cut.