Land use land cover (LULC) of city regions is strongly affected by urbanization and affects the thermal environment of urban centers by influencing the surface temperature of core city areas and their surroundings. These issues are addressed in the current study, which focuses on two provincial capitals in Pakistan, i.e., Lahore and Peshawar. Using Landsat data, LULC is determined with the aim to (a) examine the spatio-temporal changes in LULC over a period of 20 years from 1998 to 2018 using a CA-Markov model, (b) predict the future scenarios of LULC changes for the years 2023 and 2028, and (c) study the evolution of different LULC categories and investigate its impacts on land surface temperature (LST). The results for Peshawar city indicate the significant expansion in vegetation and built-up area replacing barren land. The vegetation cover and urban area of Peshawar have increased by 25.6%, and 16.3% respectively. In contrast, Lahore city urban land has expanded by 11.2% while vegetation cover decreased by (22.6%). These transitions between LULC classes also affect the LST in the study areas. Transformation of vegetation cover and water surface into built-up areas or barren land results in the increase in the LST. In contrast, the transformation of urban areas and barren land into vegetation cover or water results in the decrease in LST. The different LULC evolutions in Lahore and Peshawar clearly indicate their effects on the thermal environment, with an increasing LST trend in Lahore and a decrease in Peshawar. This study provides a baseline reference to urban planners and policymakers for informed decisions.

Fine classification of vegetation types has always been the focus and difficulty in the application field of remote sensing. Unmanned Aerial Vehicle (UAV) sensors and platforms have become important data sources in various application fields due to their high spatial resolution and flexibility. Especially, UAV hyperspectral images can play a significant role in the fine classification of vegetation types. However, it is not clear how the ultrahigh resolution UAV hyperspectral images react in the fine classification of vegetation types in highly fragmented planting areas, and how the spatial resolution variation of UAV images will affect the classification accuracy. Based on UAV hyperspectral images obtained from a commercial hyperspectral imaging sensor (S185) onboard a UAV platform, this paper examines the impact of spatial resolution on the classification of vegetation types in highly fragmented planting areas in southern China by aggregating 0.025 m hyperspectral image to relatively coarse spatial resolutions (0.05, 0.1, 0.25, 0.5, 1, 2.5 m). The object-based image analysis (OBIA) method was used and the effects of several segmentation scale parameters and different number of features were discussed. Finally, the classification accuracies from 84.3% to 91.3% were obtained successfully for multi-scale images. The results show that with the decrease of spatial resolution, the classification accuracies show a stable and slight fluctuation and then gradually decrease since the 0.5 m spatial resolution. The best classification accuracy does not occur in the original image, but at an intermediate level of resolution. The study also proves that the appropriate feature parameters vary at different scales. With the decrease of spatial resolution, the importance of vegetation index features has increased, and that of textural features shows an opposite trend; the appropriate segmentation scale has gradually decreased, and the appropriate number of features is 30 to 40. Therefore, it is of vital importance to select appropriate feature parameters for images in different scales so as to ensure the accuracy of classification.

The scope of this research lies in the combination of pre-trained Convolutional Neural Networks (CNNs) and Quantum Convolutional Neural Networks (QCNN) in application to Remote Sensing Image Scene Classification(RSISC). Deep learning (RL) is improving by leaps and bounds pretrained CNNs in Remote Sensing Image (RSI) analysis, and pre-trained CNNs have shown remarkable performance in remote sensing image scene classification (RSISC). Nonetheless, CNNs training require massive, annotated data as samples. When labeled samples are not sufficient, the most common solution is using pre-trained CNNs with a great deal of natural image datasets (e.g., ImageNet). However, these pre-trained CNNs require a large quantity of labelled data for training, which is often not feasible in RSISC, especially when the target RSIs have different imaging mechanisms from RGB natural images. In this paper, we proposed an improved hybrid classical–quantum transfer learning CNNs composed of classical and quantum elements to classify open-source RSI dataset. The classical part of the model is made up of a ResNet network which extracts useful features from RSI datasets. To further refine the network performance, a tensor quantum circuit is subsequently employed by tuning parameters on near-term quantum processors. We tested our models on the open-source RSI dataset. In our comparative study, we have concluded that the hybrid classical–quantum transferring CNN has achieved better performance than other pre-trained CNNs based RSISC methods with small training samples. Moreover, it has been proven that the proposed algorithm improves the classification accuracy while greatly decreasing the amount of model parameters and the sum of training data.

The novel infectious disease (COVID-19) took only a few weeks from its official inception in December 2019 to become a global pandemic in early 2020. Countries across the world went to lockdown, and various strict measures were implemented to reduce the further spread of the infection. Although, the strict lockdown measures were aimed at stopping the spread of COVID-19, however, Its positive implications were also observed for the environmental conditions across the global regions. The present study attempted to explore the eco-restoration of coastal marine system in response to reduced deposition of atmospheric nitrogen (NO₂) emission during the substantial shift in human activities across the global metropolitan cities. Remotely data of NO₂ emission were taken from Ozone Monitoring Instrument and the coastal water quality along the marine system was estimated from MODIS-Aqua Level-3 using Semi-Analytic Sediment Model (SASM). The changes in tropospheric NO₂ in 2020s were also compared with the long-term average changes over the baseline period 2015 − 2019. A significant reduction in anthropogenic mobility (85 − 90%) has been observed in almost all countries over different places, especially grocery, parks, workplaces, and transit stations. A massive reduction in tropospheric NO₂ was detected in Wuhan (53%), Berlin (42%), London (41%), Karachi (40%), Paris (38%), Santiago (35%), and Chennai (34%) during the strict lockdown period of the early 2020 as compared to the last five years. However, after the partial lockdown was lifted, tropospheric NO₂ values bounced back and slightly increased over Karachi (6%) and Bremen (12%). For water turbidity, the rate of reduction was found to be the highest along the different coastal regions of the Mediterranean Sea and Black Sea (51%), West Atlantic Ocean (32%), East Atlantic Ocean (29%), and Indian Ocean (21%) from Apr to Jun 2020. The monthly comparison of overland-runoff in 2020 compared to 2019 across the different costal watersheds indicates that the observed decline in turbidity might have been due to the reduced deposition of atmospheric nitrogen. The findings of this study suggest that the recent decline in tropospheric NO₂ and water turbidity might be associated with reduced emissions from fossil fuels and road transports followed by COVID-19 forced restrictions in the twenty-first century. The inferences made here highlight the hope of improving the global environmental quality by reducing greenhouse gas emissions using innovative periodic confinement measures on heavy transport and industries while securing public health and socioeconomics.

Due to the increasing capabilities of cybercriminals and the vast quantity of sensitive data, it is necessary to protect remote sensing images during data transmission with “Belt and Road” countries. Joint image compression and encryption techniques exhibit reliability and cost-effectiveness for data transmission. However, the existing methods for multiband remote sensing images have limitations, such as extensive preprocessing times, incompatibility with multiple bands, and insufficient security. To address the aforementioned issues, we propose a joint encryption and compression algorithm (JECA) for multiband remote sensing images, including a preprocessing encryption stage, crypto-compression stage, and decoding stage. In the first stage, multiple bands from an input image can be spliced together in order from left to right to generate a grayscale image, which is then scrambled at the block level by a chaotic system. In the second stage, we encrypt the DC coefficient and AC coefficient. In the final stage, we first decrypt the DC coefficient and AC coefficient, and then restore the out-of-order block through the chaotic system to get the correct grayscale image. Finally, we postprocess the grayscale image and reconstruct it into a remote sensing image. The experimental results show that JECA can reduce the preprocessing time of the sender by 50% compared to existing joint encryption and compression methods. It is also compatible with multiband remote sensing images. Furthermore, JECA improves security while maintaining the same compression ratio as existing methods, especially in terms of visual security and key sensitivity.

As one of the most important active remote sensing technologies, synthetic aperture radar (SAR) provides advanced advantages of all-day, all-weather, and strong penetration capabilities. Due to its unique electromagnetic spectrum and imaging mechanism, the dimensions of remote sensing data have been considerably expanded. Important for fundamental research in microwave remote sensing, SAR image classification has been proven to have great value in many remote sensing applications. Many widely used SAR image classification algorithms rely on the combination of hand-designed features and machine learning classifiers, which still experience many issues that remain to be resolved and overcome, including optimized feature representation, the fuzzy confusion of speckle noise, the widespread applicability, and so on. To mitigate some of the issues and to improve the pattern recognition of high-resolution SAR images, a ConvCRF model combined with superpixel boundary constraint is developed. The proposed algorithm can successfully combine the local and global advantages of fully connected conditional random fields and deep models. An optimizing strategy using a superpixel boundary constraint in the inference iterations more efficiently preserves structure details. The experimental results demonstrate that the proposed method provides competitive advantages over other widely used models. In the land cover classification experiments using the MSTAR, E-SAR and GF-3 datasets, the overall accuracy of our proposed method achieves 90.18 ± 0.37, 91.63 ± 0.27, and 90.91 ± 0.31, respectively. Regarding the issues of SAR image classification, a novel integrated learning containing local and global image features can bring practical implications.