Optical satellite images are a critical data source; however, cloud cover often compromises their quality, hindering image applications and analysis. Consequently, effectively removing clouds from ...optical satellite images has emerged as a prominent research direction. Recent advances in deep learning-based cloud removal methods have been significant, but image generation quality still needs improvement. Diffusion models have demonstrated remarkable success in diverse image-generation tasks, showcasing their potential in addressing this challenge. This paper presents a novel framework called DiffCR, which leverages conditional guided diffusion with deep convolutional networks for high-performance cloud removal for optical satellite imagery. Specifically, we introduce a decoupled encoder for conditional image feature extraction, providing a robust color representation to ensure the close similarity of appearance information between the conditional input and the synthesized output. Moreover, we propose a novel and efficient time and condition fusion block within the cloud removal model to accurately simulate the correspondence between the appearance in the conditional image and the target image at a low computational cost. Extensive experimental evaluations on three commonly used benchmark datasets demonstrate that DiffCR consistently achieves state-of-the-art performance on all metrics, with parameter and computational complexities amounting to only 5.1% and 5.4%, respectively, of those previous best methods. The source code, pre-trained models, and all the experimental results will be publicly available at https://github.com/XavierJiezou/DiffCR upon the paper's acceptance of this work.
Employing a two-step pipeline that encompasses an Image-to-Image Translation (I2I) and a Super-Resolution (SR) network, we significantly enhance satellite images with a Ground Sample Distance (GSD) ...of 30 centimeters (cm) to a superior 15 cm GSD. Our translation network learns from the characteristics of satellite images and replicates these onto aerial images with a GSD of 15 cm, creating a tailored training dataset. The super-resolution network then uses this dataset to train and render enhanced satellite images at a GSD of 15 cm. This innovative approach can provide a cost-effective substitute for commercial high-definition (HD) images, and broadens the usage of high-quality data across various applications.
This study introduces a lightweight hybrid solar photovoltaic (PV) generation prediction model operating on 1-h intervals, utilizing remote sensing data to enhance power grid management. Multisource ...remote sensing data, including spatial features from infrared satellite images and temporal data from various hourly recorded datasets, capture spatiotemporal characteristics. The model defines and synthesizes regions of interest (ROI) and surrounding areas of ROI (ROI<inline-formula> <tex-math notation="LaTeX">_{\mathrm {surr}} </tex-math></inline-formula>) within satellite images to reduce computational load. Integration of image and numerical weather prediction (NWP) process modules ensures accurate prediction. Comparative analysis against five machine learning algorithms shows significant improvements, with up to a 33.7% decrease in mean absolute error (MAE) and a 19.51% decrease in root mean square error (RMSE). Additionally, the model consistently meets ASHRAE Guideline 14 standards and outperforms single-source data models. Experimentation highlights the effectiveness of smaller ROIs in enhancing predictive accuracy, demonstrating adaptability to climate variations. This lightweight multisource remote sensing-based hybrid model promises to guide smart grid operations and sustainable power grid systems, advancing remote sensing applications in renewable energy management.
We propose an end-to-end framework for the dense, pixelwise classification of satellite imagery with convolutional neural networks (CNNs). In our framework, CNNs are directly trained to produce ...classification maps out of the input images. We first devise a fully convolutional architecture and demonstrate its relevance to the dense classification problem. We then address the issue of imperfect training data through a two-step training approach: CNNs are first initialized by using a large amount of possibly inaccurate reference data, and then refined on a small amount of accurately labeled data. To complete our framework, we design a multiscale neuron module that alleviates the common tradeoff between recognition and precise localization. A series of experiments show that our networks consider a large amount of context to provide fine-grained classification maps.
•Examines the effect of financial inclusion on roof quality among Chilean slums.•Utilizes satellite data to provide a method for assessing permanent materials among slum roofs.•Presents empirical ...evidence indicating a reduction in transaction costs as a relevant benefit resulting from financial inclusion for families residing in slums.•Identifies a positive effect of financial inclusion on roof quality among Chilean slums.•Provides evidence supporting entrepreneurship activities as a potential transmission channel through which financial inclusion affects slum-roof quality.
Although not all residents of slums are necessarily poor, and conversely, not all low-income individuals live in slums, housing precarity is a distinctive feature of these communities. This paper examines the relationship between financial inclusion and roof quality improvements for individuals living in slum settlements in Chile. We use satellite images to measure the quality of dwelling roofs as well as the CajaVecina initiative to measure the level of financial inclusion of the families that live there. Our results reveal that a higher level of financial inclusion results in an expanded presence of permanent-material roofs within slums. Moreover, we provide evidence that financial inclusion encourages self-employment activities among low-income individuals which is evidence of a transmission channel for the effect studied.
All sizes of farms can benefit from satellite imagery, not only big producers. When paired with artificial intelligence (AI) and deep machine learning techniques, satellite photography becomes an ...effective tool for monitoring agricultural conditions and anticipating issues in the field. As a result, using satellite photos to guide crop farming choices can help determine when to apply nutrients and irrigation. This paper focuses on monitoring through satellite sensors with an emphasis on the facilities offered by the European Copernicus Program through Sentinel-2 satellites the crops from a farm from Calarasi County, Borcea commune.
Land use/land cover (LULC) change and climate variability are two major factors controlling hydrological responses. The present study analyzed the separate and combined effects of these two factors ...on annual surface runoff and evapotranspiration (ET) after validating the selected models in three drought–prone watersheds of the Upper Blue Nile basin: Kasiry (highland), Kecha (midland), and Sahi (lowland). LULC maps were produced from aerial photographs and very-high-resolution satellite images from 1982, 2005/06 and 2016/17. During 1982–2016/17 the area covered by natural vegetation showed dramatic decreases, ranging from 60.2% in Kasiry to 51.8% in Sahi. In contrast, increases in cultivated land ranged from 36.7% in Kasiry to 279.6% in Sahi; the smaller increase in Kasiry resulted from the conversion of a portion of the cultivated land to an Acacia decurrens plantation after 2006. The observed LULC changes over the study period resulted in runoff increases ranging from 4% in Kecha to 28.7% in Kasiry. Climate variability in terms of annual rainfall had no significant effect on estimated runoff; whereas both LULC change and climate variability had significant effect on estimated ET. Though climate variability increased ET from 33.6% in Kecha to 42.1% in Kasiry, the LULC change related to the reduction in natural vegetation had an offsetting effect, which led to overall decreases in ET ranging from 15.8% in Kasiry to 32.8% in Kecha watershed. As changes in LULC and climate are expected to intensify in the future, it is important to study further hydrological responses considering these changes to devise future sustainable land and water management strategies.
Display omitted
•Land use/land cover change and climate variability can cause hydrological responses.•We examined 35-year trends in land use/land cover and climate in three watersheds.•Land use/land cover change caused higher surface runoff and lower evapotranspiration.•Climate variability increased evapotranspiration in all three watersheds.•Land use/land cover change had a dominant role in the hydrological responses.
•Satellite images are a valuable tool for analyzing the impact of photovoltaic plants.•Photovoltaic plants have a moderate impact on humidity (5%) and vegetation (3%).•The elimination of the contour ...of the solar panels and the comparison with external areas allows obtaining interesting analyzes.•The inclusion of vegetation cover and cultivation within the solar plant area would be beneficial for humidity.•Solar plants on areas of greater inclination of the terrain have a greater impact.
The rapid growth of photovoltaic solar energy, to achieve decarbonization, has been accompanied by increasing land occupation and the subsequent concern in the agroforestry sector. The increase in land area occupied has been of 20% in recent years, boosting solar electricity production to 5.9% of the total in Europe. This fact raises the question of the impact on vegetation greenness and moisture in the rural environment, something that has not always been considered.
Image analysis is presented as one of the most effective tools to estimate the variation of vegetation greenness and moisture. For this, terrestrial images, like those from unmanned aerial vehicles, can be used; however, this limits the amount of information available and/or increases the cost. The use of satellite images in different bands is a relatively new tool that can be exploited for the analysis of solar plants impact. This work presents a new way to use Sentinel imagery to analyse the impact of utility-scale solar plants on vegetation and moisture of the surrounding areas. According to our results, a moderate decrease in weighted index for both moisture (5%) and vegetation (3%) occurred after solar plant installation. It is expected that these results can be of help for the design of new PV and agrivoltaic plants, originating the Ground-Integrated Photovoltaics (GIPV).