Collection Of Satellite Images Research Articles

Crop health assessment through hierarchical fuzzy rule-based status maps

Precision agriculture is evolving toward a contemporary approach that involves multiple sensing techniques to monitor and enhance crop quality while minimizing losses and waste of no longer considered inexhaustible resources, such as soil and water supplies. To understand crop status, it is necessary to integrate data from heterogeneous sensors and employ advanced sensing devices that can assess crop and water status. This study presents a smart monitoring approach in agriculture, involving sensors that can be both stationary (such as soil moisture sensors) and mobile (such as sensor-equipped unmanned aerial vehicles). These sensors collect information from visual maps of crop production and water conditions, to comprehensively understand the crop area and spot any potential vegetation problems. A modular fuzzy control scheme has been designed to interpret spectral indices and vegetative parameters and, by applying fuzzy rules, return status maps about vegetation status. The rules are applied incrementally per a hierarchical design to correlate lower-level data (e.g., temperature, vegetation indices) with higher-level data (e.g., vapor pressure deficit) to robustly determine the vegetation status and the main parameters that have led to it. A case study was conducted, involving the collection of satellite images from artichoke crops in Salerno, Italy, to demonstrate the potential of incremental design and information integration in crop health monitoring. Subsequently, tests were conducted on vineyard regions of interest in Teano, Italy, to assess the efficacy of the framework in the assessment of plant status and water stress. Indeed, comparing the outcomes of our maps with those of cutting-edge machine learning (ML) semantic segmentation has indeed revealed a promising level of accuracy. Specifically, classification performance was compared to the output of conventional ML methods, demonstrating that our approach is consistent and achieves an accuracy of over 90% throughout various seasons of the year.

Regional Inversion of Soil Heavy Metal Cr Content in Agricultural Land Using Zhuhai-1 Hyperspectral Images.

With the development of hyperspectral imaging technology, the potential for utilizing hyperspectral images to accurately estimate heavy metal concentrations in regional soil has emerged. Currently, soil heavy metal inversion based on laboratory hyperspectral data has demonstrated a commendable level of accuracy. However, satellite images are susceptible to environmental factors such as atmospheric and soil background, presenting a significant challenge in the accurate estimation of soil heavy metal concentrations. In this study, typical chromium (Cr)-contaminated agricultural land in Shaoguan City, Guangdong Province, China, was taken as the study area. Soil sample collection, Cr content determination, laboratory spectral measurements, and hyperspectral satellite image collection were carried out simultaneously. The Zhuhai-1 hyperspectral satellite image spectra were corrected to match laboratory spectra using the direct standardization (DS) algorithm. Then, the corrected spectra were integrated into an optimal model based on laboratory spectral data and sample Cr content data for regional inversion of soil heavy metal Cr content in agricultural land. The results indicated that the combination of standard normal variate (SNV)+ uninformative variable elimination (UVE)+ support vector regression (SVR) model performed best with laboratory spectral data, achieving a high accuracy with an R2 of 0.97, RMSE of 5.87, MAE of 4.72, and RPD of 4.04. The DS algorithm effectively transformed satellite hyperspectral image data into spectra resembling laboratory measurements, mitigating the impact of environmental factors. Therefore, it can be applied for regional inversion of soil heavy metal content. Overall, the study area exhibited a low-risk level of Cr content in the soil, with the majority of Cr content values falling within the range of 36.21-76.23 mg/kg. Higher concentrations were primarily observed in the southeastern part of the study area. This study can provide useful exploration for the promotion and application of Zhuhai-1 image data in the regional inversion of soil heavy metals.

Long-term spatial-temporal monitoring of eutrophication in Lake Burdur using remote sensing data.

Lake eutrophication continues to be one of the major environmental challenges in lakes worldwide. This study is about using a remote sensing approach to monitor long-term chlorophyll-a (Chl-a) concentrations and the trophic state index (TSI) in Lake Burdur, Türkiye. Surface reflectance from Landsat 5, Landsat 7, and Landsat 8 satellite image collections were evaluated with an empirical equation to estimate a 38-year-long (1984-2021) time series of the lake's median Chl-a concentrations. Pixel quality masking was applied to retain only acceptable quality information and exclude images affected by cloud cover, icing, and other environmental factors from the analysis. The results were analyzed based on annual, seasonal, and monthly temporal averages. Over a period of 38 years, Chl-a concentrations were found to vary between 58.7 and 196.4 mg/m3. Notably higher concentrations were recorded in 2010 and 2021, while lower concentrations were observed between 1991 and 1993. A substantial increase in Chl-a concentration was evident from 2002 to 2010. The maximum concentration of Chl-a during the first two decades of the analysis was 130 mg/m3, which increased to 200 mg/m3 during the last two decades. Landsat-derived TSI values suggested that Lake Burdur has been mostly hypertrophic for the entire study period.

LASSO (L1) Regularization for Development of Sparse Remote-Sensing Models with Applications in Optically Complex Waters Using GEE Tools

Remote-sensing data are used extensively to monitor water quality parameters such as clarity, temperature, and chlorophyll-a (chl-a) content. This is generally achieved by collecting in situ data coincident with satellite data collections and then creating empirical water quality models using approaches such as multi-linear regression or step-wise linear regression. These approaches, which require modelers to select model parameters, may not be well suited for optically complex waters, where interference from suspended solids, dissolved organic matter, or other constituents may act as “confusers”. For these waters, it may be useful to include non-standard terms, which might not be considered when using traditional methods. Recent machine-learning work has demonstrated an ability to explore large feature spaces and generate accurate empirical models that do not require parameter selection. However, these methods, because of the large number of included terms involved, result in models that are not explainable and cannot be analyzed. We explore the use of Least Absolute Shrinkage and Select Operator (LASSO), or L1, regularization to fit linear regression models and produce parsimonious models with limited terms to enable interpretation and explainability. We demonstrate this approach with a case study in which chl-a models are developed for Utah Lake, Utah, USA., an optically complex freshwater body, and compare the resulting model terms to model terms from the literature. We discuss trade-offs between interpretability and model performance while using L1 regularization as a tool. The resulting model terms are both similar to and distinct from those in the literature, thereby suggesting that this approach is useful for the development of models for optically complex water bodies where standard model terms may not be optimal. We investigate the effect of non-coincident data, that is, the length of time between satellite image collection and in situ sampling, on model performance. We find that, for Utah Lake (for which there are extensive data available), three days is the limit, but 12 h provides the best trade-off. This value is site-dependent, and researchers should use site-specific numbers. To document and explain our approach, we provide Colab notebooks for compiling near-coincident data pairs of remote-sensing and in situ data using Google Earth Engine (GEE) and a second notebook implementing L1 model creation using scikitlearn. The second notebook includes data-engineering routines with which to generate band ratios, logs, and other combinations. The notebooks can be easily modified to adapt them to other locations, sensors, or parameters.

Quantification of landscape metrics effects on downscaled urban land surface temperature accuracy of satellite imagery

Improving the spatial resolution of Land Surface Temperature (LST) obtained from satellite images is of great importance in various applications, especially in urban areas. Aiming to bridge the gap in the research background, this study attempted to quantify the effect of landscape metrics on the accuracy of urban LST downscaling. The research data included a collection of satellite images from Landsat and Terra satellites and auxiliary data of nine European cities, namely Lisbon, Madrid, Bucharest, Vienna, Prague, Paris, Copenhagen, Stockholm, and Helsinki. In the first stage, surface biophysical, topographic, and thematic property maps affecting the spatial distribution of LST were prepared. Secondly, the effect of the endogenous (influence of intra-pixel properties) and exogenous (influence of landscape metrics) variables of each surface property on LST was evaluated in warm and cold seasonal conditions. Finally, the effect of landscape metrics on the accuracy of LST downscaling from 960 m to 30 m was quantified. The results showed that the mean absolute correlation coefficient (r) values between the endogenous (exogenous) effects of surface biophysical, topographic, and thematic properties and LST in the cold season were 0.25 (0.12), 0.19 (0.06), and 0.09 (0.04), respectively. For the warm season, these values were 0.55 (0.24), 0.11 (0.03), and 0.23 (0.09), respectively. The mean r (root-mean-square error (RMSE)) between the actual LST and downscaled LST (DLST) obtained by considering only the endogenous effects in the cold and warm seasons were 0.79 (0.66) and 0.87 (1.38 °C), respectively. Considering the simultaneous effect of endogenous and exogenous variables in LST downscaling, these values reached 0.83 (0.47) and 0.91 (0.99 °C), respectively. The greatest effect of landscape metrics on the accuracy of LST downscaling was associated with built-up lands. Accounting for landscape metrics in the downscaling process significantly increases the accuracy of downscaled LST.

Ekstraksi Perubahan Tutupan Vegetasi Di Kabupaten Gorontalo Menggunakan Google Earth Engine

Monitoring changes in vegetation cover is important for the restoration of ecosystems in the Gorontalo Regency area. The utilization of remote sensing technology makes it possible to detect the dynamics of changes in vegetation cover spatially and temporally. The Terra MODIS satellite image collection in the study area is available in large numbers and sizes. Therefore, cloud computing-based spatial technology support is needed. Google Earth Engine (GEE) as a geospatial computing device is an alternative to cover this shortfall. The aim of this study is to explore the condition of vegetation cover spatially and temporally using the GEE platform. A total of 43 MODIS images in the study area, recording periods 2000 and 2020, were used to quickly and effectively generate vegetation cover maps. The process of downloading, processing, and analyzing data was automated through the GEE interface. The results of the mapping in 2000 and 2020 are shown by maps of vegetation cover in two classes, namely; vegetation and non-vegetation. The accuracy of the vegetation cover map shows good results, namely an overall accuracy of 0.81 for 2000 and 0.85 for 2020. The area of the non-vegetation class increased by 2815.29 ha, and the vegetation class decreased by 2767.31 ha. The map of spatial changes in vegetation cover in the study area is classified into three classes, namely revegetation, devegetation, and unchanged. Based on these results, the extraction of vegetation cover changes in the study area using the GEE platform can be carried out well.

Environmental degradation through mining for energy resources: The case of the shrinking Laguna Santa Rosa wetland in the Atacama Region of Chile

As the world strives to replace fossil fuels with clean energy – reflected by global surge in the number of electric vehicles – the environmental impact of mining all the lithium (Li) needed to enable such a transformation has become a problem in its own right. In South America, the biggest problem is the excessive use of water in Li extraction process in one of the driest areas in the world. Apart from causing severe friction over water rights between local communities and mining companies, it puts enormous pressure on the region's fragile and poorly understood wetland ecosystems. Wetlands are one of the most threatened ecosystems on the Earth, despite their great importance as habitats for a vast number of species and corresponding to one of the most productive environments. Present work is the outcome of an investigation on Laguna Santa Rosa's (LSR) vulnerability resulting from ongoing metal mining operations in its surroundings that require a large volume of water extracted from local aquifers, in addition to a high evaporation rate in the area. This groundwater-dependent wetland will soon be further vulnerable with the commencement of water-intensive Li mining at Salar de Maricunga, with the extraction project already having an environmental impact study approved. Sustainability of this wetland protected under the Ramsar Convention and home to numerous wildlife species habiting this highland sector of the Andean Cordillera is vital for the associated ecosystems. The variation in the water surface area of LSR has been deciphered through the application of a Landsat-5 Thematic Mapper (TM) satellite image collection. This has been done both for the hydrological year 2016–2017 and 1993-2014 period. A decreasing trend in the water surface area of LSR, a hypersaline lake at the southern extreme of Salar de Maricunga, a salt flat in the Atacama Region of Chile, was observed through the study of satellite images between 1993 and 2014, showing shrinking of this wetland. However, this shrinking trend was punctuated by extreme rainfall and consequent flood with accumulated precipitation exceeding 40 mm in a single day and hourly mean rainfall rates higher than 10 mm/h recorded at several locations in the hyperarid Atacama Desert on March 25, 2015. This raised the lake's water level, and thus the areal extent of the lake water observed in the satellite images of the 2016–2017 hydrological year following the extreme weather events of 2015. The interplay of such extreme weather events and groundwater extraction for mining activities in the area complicates the assessment of the latter's effect on LSR, as the evaluation is constrained to the intervals between successive extreme weather events. In addition, the water level increases in summer because of the thawing of the snow. Close monitoring of the wetlands like LSR is essential to ensure their sustainability by considering both anthropic and climatic factors.

Fine-scale soil mapping with Earth Observation data: a multiple geographic level comparison

Multitemporal collections of satellite images and their products have recently been explored in digital soil mapping. This study aimed to produce a bare soil image (BSI) for the São Paulo State (Brazil) to perform a pedometric analysis for different geographical levels. First, we assessed the potential of the BSI for predicting the surface (0.00-0.20 m) and subsurface (0.80-1.00 m) clay, iron oxides (Fe 2 O 3 ), aluminum (m%) and bases saturation (V%) contents at the state level, which [...]

Geographic Optimal Transport for Heterogeneous Data: Fusing Remote Sensing and Social Media

The fusion of heterogeneous remote sensing and social media data can fill the gaps in satellite image collections and improve the spatiotemporal resolution of the available data sets. As a result, it is being gradually adopted in multimodal data analytics. Generally, the fusion of heterogeneous geographic data faces the following issues: 1) the probability density functions may differ from different data sources and 2) the geolocations may not be well aligned. The former one can be generally solved by performing an alignment of representations in the source and target domains using, for instance, domain adaptation. The latter issue is seldom considered in the fusion of heterogeneous geographic data. In this article, we present a new method called geographic optimal transport (GOT), which aims at aligning representations and geolocations in a simultaneous fashion. A flood event that took place in 2013 in Boulder, CO, USA, is taken as a case study to evaluate our GOT method. Here, we consider two remote sensing features derived from water indicators, i.e., the normalized difference vegetation index (NDVI) and the normalized difference water index (NDWI), for the fusion of Landsat 8 imagery and Twitter data. A comparison between our newly developed GOT and the traditional optimal transport (OT) is performed. Experimental results demonstrate that the proposed GOT can accurately align spatially biased georeferenced tweets to the flood phenomena, leading to the conclusion that GOT can effectively fuse heterogeneous remote sensing and social media data.

COVID-19 and surface water quality: Improved lake water quality during the lockdown

Human life comes to a standstill as many countries shut themselves off from the work due to the novel coronavirus disease pandemic (COVID-19) that hit the world severely in the first quarter of 2020. All types of industries, vehicle movement, and people's activity suddenly halted, perhaps for the first time in modern history. For a long time, it has been stated in various literature that the increased industrialization and anthropogenic activities in the last two decades polluted the atmosphere, hydrosphere, and biosphere. Since the industries and people's activities have been shut off for a month or more in many parts of the world, it is expected to show some improvement in the prevailing conditions in the aforementioned spheres of environment. Here, with the help of remote sensing images, this work quantitatively demonstrated the improvement in surface water quality in terms of suspended particulate matter (SPM) in the Vembanad Lake, the longest freshwater lake in India. The SPM estimated based on established turbidity algorithm from Landsat-8 OLI images showed that the SPM concentration during the lockdown period decreased by 15.9% on average (range: −10.3% to 36.4%, up to 8 mg/l decrease) compared with the pre-lockdown period. Time series analysis of satellite image collections (April 2013 – April 2020) showed that the SPM quantified for April 2020 is the lowest for 11 out of 20 zones of the Vembanad lake. When compared with preceding years, the percentage decrease in SPM for April 2020 is up to 34% from the previous minima.

Sliding Time Master Digital Image Correlation Analyses of CubeSat Images for landslide Monitoring: The Rattlesnake Hills Landslide (USA)

Landslide monitoring is a global challenge that can take strong advantage from opportunities offered by Earth Observation (EO). The increasing availability of constellations of small satellites (e.g., CubeSats) is allowing the collection of satellite images at an incredible revisit time (daily) and good spatial resolution. Furthermore, this trend is expected to grow rapidly in the next few years. In order to explore the potential of using a long stack of images for improving the measurement of ground displacement, we developed a new procedure called STMDA (Slide Time Master Digital image correlation Analyses) that we applied to one year long stack of PlanetScope images for back analyzing the displacement pattern of the Rattlesnake Hills landslide occurred between the 2017 and 2018 in the Washington State (USA). Displacement maps and time-series of displacement of different portions of the landslide was derived, measuring velocity up to 0.5 m/week, i.e., very similar to velocities available in literature. Furthermore, STMDA showed also a good potential in denoising the time-series of displacement at the whole scale with respect to the application of standard DIC methods, thus providing displacement precision up to 0.01 pixels.

Siamese Convolutional Neural Networks for Remote Sensing Scene Classification

The convolutional neural networks (CNNs) have shown powerful feature representation capability, which provides novel avenues to improve scene classification of remote sensing imagery. Although we can acquire large collections of satellite images, the lack of rich label information is still a major concern in the remote sensing field. In addition, remote sensing data sets have their own limitations, such as the small scale of scene classes and lack of image diversity. To mitigate the impact of the existing problems, a Siamese CNN, which combines the identification and verification models of CNNs, is proposed in this letter. A metric learning regularization term is explicitly imposed on the features learned through CNNs, which enforce the Siamese networks to be more robust. We carried out experiments on three widely used remote sensing data sets for performance evaluation. Experimental results show that our proposed method outperforms the existing methods.

On-Demand Processing of Data Cubes from Satellite Image Collections with the gdalcubes Library

Earth observation data cubes are increasingly used as a data structure to make large collections of satellite images easily accessible to scientists. They hide complexities in the data such that data users can concentrate on the analysis rather than on data management. However, the construction of data cubes is not trivial and involves decisions that must be taken with regard to any particular analyses. This paper proposes on-demand data cubes, which are constructed on the fly when data users process the data. We introduce the open-source C++ library and R package gdalcubes for the construction and processing of on-demand data cubes from satellite image collections, and show how it supports interactive method development workflows where data users can initially try methods on small subsamples before running analyses on high resolution and/or large areas. Two study cases, one on processing Sentinel-2 time series and the other on combining vegetation, land surface temperature, and precipitation data, demonstrate and evaluate this implementation. While results suggest that on-demand data cubes implemented in gdalcubes support interactivity and allow for combining multiple data products, the speed-up effect also strongly depends on how original data products are organized. The potential for cloud deployment is discussed.

Missed carbon emissions from forests: comparing countries’ estimates submitted to UNFCCC to biophysical estimates

Reducing forest loss has the potential to reduce global carbon emissions, but paying countries to do so will only work if activities are targeting areas with rapid deforestation or high threat. As of December 2017, 25 countries reported their benchmark greenhouse gas emissions from forests (‘reference levels’) under the United Nations Framework Convention on Climate Change, with the aim of receiving payments if they end up releasing less or removing more. There remains however a question as to whether the eventual emission trajectories compared to these reference levels represent real emission reductions, as the benchmarks rely on a variety of different methods and limited datasets. To examine whether the forest areas historically associated with significant emissions are targeted in the reference levels, we compared the forest area estimates submitted by seven countries in Asia and the Pacific (Cambodia, Indonesia, Malaysia, Nepal, Papua New Guinea, Sri Lanka, and Vietnam) with forest area estimates using the Global Forest Change v1.4 (GFC) dataset from 2000–2016, processed to closely match national forest definitions. GFC provides standardised tree cover change data based on biophysical characteristics using an extensive collection of satellite images. We found consistent differences, with most countries reporting considerably less forest loss than the GFC-based analysis. These differences are due to the countries’ selection of activities to report, as well as their choice of forest types and land use, defining the forest areas to be monitored. Our study highlights an urgent need to address the gap between the forests monitored by countries and those sources of emissions. The current approaches, even successfully implemented, may not lead to emission reductions, thereby challenging the effectiveness of carbon payments.

Traditional Coastal Settlements of Chaoshan Area Adapted to The Sand Ridge Landform

Sand ridge landform is a kind of typical coastal natural landform in Chaoshan area. Through data review, historical satellite image collection, field interviews, archives search and other methods, the relevant data of the sand ridge landform area were collected, and comparative research methods were used to analyze the influence of such terrain on the Traditional settlement mode. A types of settlement patterns is summarized: the evolutionary pattern of settlements which are built on high ground and spread out to sea and that are adapted to the development of sand ridges landform. Through this case study, we hope to have a better understanding of the characteristics of the Chaoshan traditional settlements.

Weakly supervised vehicle detection in satellite images via multi-instance discriminative learning

Vehicle detection in satellite images has attracted extensive research interest with widespreading application potentials. The main challenge lies in the difficulty of labeling sufficient training instances (vehicle rectangles) across all resolutions and imaging conditions of satellite images, which degenerates the performance of vehicle detectors trained correspondingly. To tackle this challenge, in this paper we propose an intelligent and labor-light scheme for large-scale training of vehicle detectors. Our scheme only requires region-level group annotation, i.e. whether this region contains vehicle(s) or not, without explicitly labeling the bounding boxes of vehicles. To this end, a novel weakly supervised, multi-instance learning algorithm is designed to learn instance-wise vehicle detectors from such “weak labels”. In particular, a density estimator is firstly adopted to estimate the density map of vehicle instances from the positive regions. Then, a multi-instance SVM is trained to classify and locate vehicle instances from this map. We have carried out extensive experiments on a large-scale satellite image collection that contains various resolutions and imaging conditions. We have demonstrated that the proposed scheme has achieved superior performance by comparing to a set of state-of-the-art and alternative approaches.

Satellite image collection modeling for large area hazard emergency response

Timely collection of critical hazard information is the key to intelligent and effective hazard emergency response decisions. Satellite remote sensing imagery provides an effective way to collect critical information. Natural hazards, however, often have large impact areas – larger than a single satellite scene. Additionally, the hazard impact area may be discontinuous, particularly in flooding or tornado hazard events. In this paper, a spatial optimization model is proposed to solve the large area satellite image acquisition planning problem in the context of hazard emergency response. In the model, a large hazard impact area is represented as multiple polygons and image collection priorities for different portion of impact area are addressed. The optimization problem is solved with an exact algorithm. Application results demonstrate that the proposed method can address the satellite image acquisition planning problem. A spatial decision support system supporting the optimization model was developed. Several examples of image acquisition problems are used to demonstrate the complexity of the problem and derive optimized solutions.

Citizen Science in Archaeology

Copyright © 2014 by the Society for American Archaeology. Citizen science, as a process of volunteer participation through crowdsourcing, facilitates the creation of mass data sets needed to address subtle and large-scale patterns in complex phenomena. Citizen science efforts in other field disciplines such as biology, geography, and astronomy indicate how new web-based interfaces can enhance and expand upon archaeologists' existing platforms of volunteer engagement such as field schools, community archaeology, site stewardship, and professional-avocational partnerships. Archaeological research can benefit from the citizen science paradigm in four ways: fieldwork that makes use of widely available technologies such as mobile applications for photography and data upload; searches of large satellite image collections for site identification and monitoring; crowdfunding; and crowdsourced computer entry of heritage data.

Citizen Science in Archaeology

Abstract Citizen science, as a process of volunteer participation through crowdsourcing, facilitates the creation of mass data sets needed to address subtle and large-scale patterns in complex phenomena. Citizen science efforts in other field disciplines such as biology, geography, and astronomy indicate how new web-based interfaces can enhance and expand upon archaeologists’ existing platforms of volunteer engagement such as field schools, community archaeology, site stewardship, and professional–avocational partnerships. Archaeological research can benefit from the citizen science paradigm in four ways: fieldwork that makes use of widely available technologies such as mobile applications for photography and data upload; searches of large satellite image collections for site identification and monitoring; crowdfunding; and crowdsourced computer entry of heritage data.

Use of Neural Networks for Automatic Classification From High-Resolution Images

The effectiveness of multilayer perceptron (MLP) networks as a tool for the classification of remotely sensed images has been already proven in past years. However, most of the studies consider images characterized by high spatial resolution (around 15-30 m) while a detailed analysis of the performance of this type of classifier on very high resolution images (around 1-2 m) such as those provided by the Quickbird satellite is still lacking. Moreover, the classification problem is normally understood as the classification of a single image while the capabilities of a single network of performing automatic classification and feature extraction over a collection of archived images has not been explored so far. In this paper, besides assessing the performance of MLP for the classification of very high resolution images, we investigate on the generalization capabilities of this type of algorithms with the purpose of using them as a tool for fully automatic classification of collections of satellite images, either at very high or at high-resolution. In particular, applications to urban area monitoring have been addressed