In this paper, we present a patch-based land use and land cover classification approach using Sentinel-2 satellite images. The Sentinel-2 satellite images are openly and freely accessible, and are ...provided in the earth observation program Copernicus. We present a novel dataset, based on these images that covers 13 spectral bands and is comprised of ten classes with a total of 27 000 labeled and geo-referenced images. Benchmarks are provided for this novel dataset with its spectral bands using state-of-the-art deep convolutional neural networks. An overall classification accuracy of 98.57% was achieved with the proposed novel dataset. The resulting classification system opens a gate toward a number of earth observation applications. We demonstrate how this classification system can be used for detecting land use and land cover changes, and how it can assist in improving geographical maps. The geo-referenced dataset EuroSAT is made publicly available at https://github.com/phelber/eurosat.
•A satellite image-based photovoltaic power forecasting model is proposed.•A nonlinear cloud movement forecasting method based on deep learning is proposed.•An algorithm for intra-hour cloud ...condition estimation is established.•An algorithm for recognizing the cloud region that blocks sunlight is designed.
The rapid variation of clouds is the main factor that causes the fluctuation of photovoltaic power.11This work was supported by the National Key Research and Development Program of China under Grant 2019YFE0118400.The satellite images contain plenty of information about clouds, applicable for photovoltaic power forecast. However, in practice, two main factors obstruct the application of the satellite images: 1) the relatively low update frequency of the satellite images mismatches the photovoltaic power forecasting frequency, and 2) the cloud region that blocks the sunlight changes significantly with time. In this paper, a novel satellite image-based approach for photovoltaic power forecast is proposed to overcome these obstacles and achieve accurate forecasting results. Firstly, concerning the hourly updated satellite images, a nonlinear cloud movement forecasting model, considering the thickness and shape changes of the cloud, is presented to forecast the hourly variation of the images. Secondly, an active cloud region selection rule is derived based on the changing solar position to dynamically select the cloud region that blocks the concerned photovoltaic power station in a satellite image. Thirdly, a sequential cloud region selection algorithm is provided to estimate the intra-hour variation of the cloud to match the photovoltaic power forecasting frequency. Finally, the photovoltaic power is predicted using the XGBoost algorithm concerning the effects of the cloud and other influencing factors. Testing results show that the proposed method can achieve more accurate photovoltaic power forecasts using the low update frequency satellite images. Meanwhile, the superior performance compared with other benchmarks also verifies the effectiveness of considering cloud information obtained by the proposed method for photovoltaic power forecast.
Disaster relief, police work, and environmental monitoring all benefit from satellite images. Objects and infrastructure in the images must be manually identified for these applications. Due to the ...large areas that need to be searched and the limited number of accessible analysts, automation is essential. However, the accuracy and dependability of existing object recognition and classification algorithms renders them inadequate for the task. One family of machine learning algorithms called "deep learning" has showed immense potential for automating these kinds of jobs. Convolutional neural networks have been successful in the area of image recognition. Here, convolutional neural networks (CNNs) and a particle swarm optimization classifier is utilized to develop efficient algorithms for classifying satellite images. The results of this classifier model are better than those of existing approaches.
A contaminação ou poluição da água, geram diversos fenômenos, um deles é a eutrofização. Em virtude disso, com a finalidade de gestão sustentável dos recursos hídricos, o Índice de Estado Trófico foi ...desenvolvido para possibilitar a classificação das águas de corpos hídricos em diferentes graus de trofia, sendo o sensoriamento remoto uma das ferramentas capazes de determinar tal índice. Dessa forma, o objetivo deste estudo é comparar os níveis tróficos obtidos por meio das análises do sensoriamento remoto com as análises limnológicas de amostras de clorofila “a” em laboratório. A presente pesquisa é composta por três etapas de análises, primeiro serão coletadas amostras de água ao longo de sete pontos da baía de Portel-PA, que por sua vez serão analisadas em laboratório, em seguida, será feita a coleta e o tratamento das imagens de satélite para a predição da clorofila “a”, e então a comparação qualitativa dos valores obtidos com as etapas anteriores através do IET. A aplicação da metodologia permitiu observar que em todos os pontos os valores de IET verificados pelo sensoriamento remoto estão próximos da análise feita em laboratório tendo como classificação predominante entre os pontos a mesotrófica. Logo, análises espaciais como esta, demonstram a importância do sensoriamento remoto como ferramenta para a identificação das áreas de ocorrência de clorofila “a”, contudo, as técnicas de sensoriamento remoto utilizadas neste trabalho, não foram capazes de substituir os trabalhos de campo. Elas apenas permitiram um planejamento e monitoramento remoto mais eficiente das ações a serem realizadas na etapa conclusiva.
In recent years, large amount of high spatial-resolution remote sensing (HRRS) images are available for land-cover mapping. However, due to the complex information brought by the increased spatial ...resolution and the data disturbances caused by different conditions of image acquisition, it is often difficult to find an efficient method for achieving accurate land-cover classification with high-resolution and heterogeneous remote sensing images. In this paper, we propose a scheme to apply deep model obtained from labeled land-cover dataset to classify unlabeled HRRS images. The main idea is to rely on deep neural networks for presenting the contextual information contained in different types of land-covers and propose a pseudo-labeling and sample selection scheme for improving the transferability of deep models. More precisely, a deep Convolutional Neural Networks (CNNs) is first pre-trained with a well-annotated land-cover dataset, referred to as the source data. Then, given a target image with no labels, the pre-trained CNN model is utilized to classify the image in a patch-wise manner. The patches with high confidence are assigned with pseudo-labels and employed as the queries to retrieve related samples from the source data. The pseudo-labels confirmed with the retrieved results are regarded as supervised information for fine-tuning the pre-trained deep model. To obtain a pixel-wise land-cover classification with the target image, we rely on the fine-tuned CNN and develop a hybrid classification by combining patch-wise classification and hierarchical segmentation. In addition, we create a large-scale land-cover dataset containing 150 Gaofen-2 satellite images for CNN pre-training. Experiments on multi-source HRRS images, including Gaofen-2, Gaofen-1, Jilin-1, Ziyuan-3, Sentinel-2A, and Google Earth platform data, show encouraging results and demonstrate the applicability of the proposed scheme to land-cover classification with multi-source HRRS images.
•A method to learn transferable deep model for 5-class land-cover (LC) classification.•A labeled dataset consisting of 150 Gaofen-2 images for LC classification.•It improves LC classification performance about 20% using multi-source RS images.•The method shows good transferability on different sensors and geolocations.
Lack of planning and regulations around the landfills has resulted and continues to result in severe environmental damage to the immediate environment around the landfills. Our study systematically ...reviews the literature to understand different processes of monitoring and analysis of a waste disposal site. It further analyses a satellite footprint from Google Earth Engine, of the western part of India around the urban area of Bombay. For the satellite footprint, we compare different algorithms and satellites for detecting landfills using machine learning. We conduct a supervised classification for satellite images for Land Satellite Applied to Remote Sensing (LANDSAT) (2013 to 2023) and SENTINEL (2018 to 2023) using three different classification algorithms: CART (Classification and Regression Tree), Naive Bayes and SVM (Support Vector Machine). The LANDSAT SVM model was generally the most stable and consistently performed well. The model consistently has one of the highest accuracy scores over the years, followed closely by SENTINEL SVM. The analysis can be replicated to other cities and other large-area studies, and can act as a pointer in doing further analysis of the landfill that can further be used to prevent the effects of the waste disposal site on its surrounding environment.
In this study, we propose a robust debris estimation model applied to satellite imagery that is suitable for practical applications. In our previous study, we proposed a coastal marine debris ...estimation model using semantic segmentation applied to very high-resolution satellite images. We identified limitations when applying the model to various lower spatial and spectral resolution satellite images or to areas with fewer satellite images cases. To overcome these limitations, we now employed unsupervised domain adaptation (UDA) techniques to transfer the earlier model to these lower resolution or fewer satellite images. These domain adaptation techniques consider differences in spatial feature distributions and/or satellite sensor characteristics. We confirmed the ability of UDA to classify Planet Skysat and Airbus Pleiades images using MAXAR WorldView images to generate an accurate segmentation map. The UDA, then, allows us to analyze the lower satellite images without the need to independently generate new segmentation labels. We conducted statistical analyses and demonstrated the high correlation between the local debris cleanup data and entropy metrics computed using our UDA approach. Our method enhances the sampling frequency of satellite images by analyzing lower resolution imagery, allowing monthly to weekly, or even daily intervals, and facilitates rapid estimation utilizing fewer images, thereby providing an invaluable tool for coastal debris characterization and assessment.