Pub Date : 2020-03-01DOI: 10.1109/LAGIRS48042.2020.9165596
A. A. Dos Reis, B. C. Silva, J. P. Werner, Y. F. Silva, J. Rocha, G. Figueiredo, J. Antunes, J. Esquerdo, A. Coutinho, R. Lamparelli, P. G. Magalhães
Pasture biomass information is essential to monitor forage resources in grazed areas, as well as to support grazing management decisions. The increasing temporal and spatial resolutions offered by the new generation of orbital platforms, such as Planet CubeSat satellites, have improved the capability of monitoring pasture biomass using remotely-sensed data. In a preliminary study, we investigated the potential of spectral variables derived from PlanetScope imagery to predict pasture biomass in an area of Integrated Crop-Livestock System (ICLS) in Brazil. Satellite and field data were collected during the same period (May – August 2019) for calibration and validation of the relation between predictor variables and pasture biomass using the Random Forest (RF) regression algorithm. We used as predictor variables 24 vegetation indices derived from PlanetScope imagery, as well as the four PlanetScope bands, and field management information. Pasture biomass ranged from approximately 24 to 656 g$.mathrm{m}^{-2}$, with a coefficient of variation of 54.96%. Near Infrared Green Simple Ratio (NIR/Green), Green Leaf Algorithm (GLA) vegetation indices and days after sowing (DAS) are among the most important variables as measured by the RF Variable Importance metric in the best RF model predicting pasture biomass, which resulted in Root Mean Square Error (RMSE) of 52.04 g$.mathrm{m}^{-2}(32.75$%). Accurate estimates of pasture biomass using spectral variables derived from PlanetScope imagery are promising, providing new insights into the opportunities and limitations related to the use of PlanetScope imagery for pasture monitoring.
{"title":"Exploring the Potential of High-Resolution Planetscope Imagery for Pasture Biomass Estimation in an Integrated Crop–Livestock System","authors":"A. A. Dos Reis, B. C. Silva, J. P. Werner, Y. F. Silva, J. Rocha, G. Figueiredo, J. Antunes, J. Esquerdo, A. Coutinho, R. Lamparelli, P. G. Magalhães","doi":"10.1109/LAGIRS48042.2020.9165596","DOIUrl":"https://doi.org/10.1109/LAGIRS48042.2020.9165596","url":null,"abstract":"Pasture biomass information is essential to monitor forage resources in grazed areas, as well as to support grazing management decisions. The increasing temporal and spatial resolutions offered by the new generation of orbital platforms, such as Planet CubeSat satellites, have improved the capability of monitoring pasture biomass using remotely-sensed data. In a preliminary study, we investigated the potential of spectral variables derived from PlanetScope imagery to predict pasture biomass in an area of Integrated Crop-Livestock System (ICLS) in Brazil. Satellite and field data were collected during the same period (May – August 2019) for calibration and validation of the relation between predictor variables and pasture biomass using the Random Forest (RF) regression algorithm. We used as predictor variables 24 vegetation indices derived from PlanetScope imagery, as well as the four PlanetScope bands, and field management information. Pasture biomass ranged from approximately 24 to 656 g$.mathrm{m}^{-2}$, with a coefficient of variation of 54.96%. Near Infrared Green Simple Ratio (NIR/Green), Green Leaf Algorithm (GLA) vegetation indices and days after sowing (DAS) are among the most important variables as measured by the RF Variable Importance metric in the best RF model predicting pasture biomass, which resulted in Root Mean Square Error (RMSE) of 52.04 g$.mathrm{m}^{-2}(32.75$%). Accurate estimates of pasture biomass using spectral variables derived from PlanetScope imagery are promising, providing new insights into the opportunities and limitations related to the use of PlanetScope imagery for pasture monitoring.","PeriodicalId":111863,"journal":{"name":"2020 IEEE Latin American GRSS & ISPRS Remote Sensing Conference (LAGIRS)","volume":"762 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2020-03-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"133251636","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2020-03-01DOI: 10.1109/LAGIRS48042.2020.9165592
A. F. Bonamigo, J. D. Oliveira, R. Lamparelli, G. Figueiredo, E. Campbell, J. Soares, L. Monteiro, M. Vianna, D. Jaiswal, J. Sheehan, L. Lynd
Brazil is one of the largest exporters of cattle meat production. Most of this production is under pasture areas, with different levels of livestock and field management. Remotely sensed images could be interesting tools to detect distinct temporal and spatial patterns of these systems. In this context, classification algorithms have been proposed to use information from satellite images to map different land covers. The Time-Weighted Dynamic Time Warping (TWDTW) is an algorithm that has the advantage of working well with datasets with enough amounts of temporal information and seasonality patterns. In the present work, the TWDTW was performed to classify pasture managements in farms located in Western region of São Paulo State in Brazil for the years 2017 and 2018, as a primary study. It was used Normalized Difference Vegetation Index (NDVI) time series images from Moderate Resolution Imaging Spectroradiometer – MODIS sensor (products MOD13Q1 and MYD13Q) with 250 meters of spatial resolution. In classifications for the years 2017 and 2018, it was observed a predominance of traditional pasture. Total areas of degraded and traditional pasture were very similar between 2017 and 2018. The year of 2017 showed higher spatial distribution of intensified pastures than year 2018. The classification achieved satisfying results with complete accuracy in validation. The information collected from field visits were important to analyse general aspects of the results. Therefore, in this pilot study TWDTW algorithm demonstrated to have potential in differentiating classes of pasture management. Next steps will be to explor e the possibilities to classify pasture systems in large areas.
{"title":"Mapping Pasture Areas In Western Region Of SÃO Paulo State, Brazil","authors":"A. F. Bonamigo, J. D. Oliveira, R. Lamparelli, G. Figueiredo, E. Campbell, J. Soares, L. Monteiro, M. Vianna, D. Jaiswal, J. Sheehan, L. Lynd","doi":"10.1109/LAGIRS48042.2020.9165592","DOIUrl":"https://doi.org/10.1109/LAGIRS48042.2020.9165592","url":null,"abstract":"Brazil is one of the largest exporters of cattle meat production. Most of this production is under pasture areas, with different levels of livestock and field management. Remotely sensed images could be interesting tools to detect distinct temporal and spatial patterns of these systems. In this context, classification algorithms have been proposed to use information from satellite images to map different land covers. The Time-Weighted Dynamic Time Warping (TWDTW) is an algorithm that has the advantage of working well with datasets with enough amounts of temporal information and seasonality patterns. In the present work, the TWDTW was performed to classify pasture managements in farms located in Western region of São Paulo State in Brazil for the years 2017 and 2018, as a primary study. It was used Normalized Difference Vegetation Index (NDVI) time series images from Moderate Resolution Imaging Spectroradiometer – MODIS sensor (products MOD13Q1 and MYD13Q) with 250 meters of spatial resolution. In classifications for the years 2017 and 2018, it was observed a predominance of traditional pasture. Total areas of degraded and traditional pasture were very similar between 2017 and 2018. The year of 2017 showed higher spatial distribution of intensified pastures than year 2018. The classification achieved satisfying results with complete accuracy in validation. The information collected from field visits were important to analyse general aspects of the results. Therefore, in this pilot study TWDTW algorithm demonstrated to have potential in differentiating classes of pasture management. Next steps will be to explor e the possibilities to classify pasture systems in large areas.","PeriodicalId":111863,"journal":{"name":"2020 IEEE Latin American GRSS & ISPRS Remote Sensing Conference (LAGIRS)","volume":"1 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2020-03-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"130989307","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2020-03-01DOI: 10.1109/LAGIRS48042.2020.9165621
M. G. Lacerda, E. H. Shiguemori, A. Damiao, C. S. Anjos, M. Habermann
Given the wide variety of image classifiers available nowadays, some questions remain about the accuracy and processing time of Very High Resolution (VHR) images. Another question concerns the use of a Single or Ensemble Classifiers. Of course, the main factor to consider is the quality of the classified image, but computational cost is also important, especially in applications that require real-time processing. Given this scenario, this paper aims to relate the accuracy of seven single classifiers and the ensemble of the same classifiers with the processing time. In this paper the ensemble of classifiers had the best results in terms of accuracy, however, it comes to processing time, the decision tree had the best performance.
{"title":"Analysis of VHR Image Classification by Single and Ensemble of Classifiers","authors":"M. G. Lacerda, E. H. Shiguemori, A. Damiao, C. S. Anjos, M. Habermann","doi":"10.1109/LAGIRS48042.2020.9165621","DOIUrl":"https://doi.org/10.1109/LAGIRS48042.2020.9165621","url":null,"abstract":"Given the wide variety of image classifiers available nowadays, some questions remain about the accuracy and processing time of Very High Resolution (VHR) images. Another question concerns the use of a Single or Ensemble Classifiers. Of course, the main factor to consider is the quality of the classified image, but computational cost is also important, especially in applications that require real-time processing. Given this scenario, this paper aims to relate the accuracy of seven single classifiers and the ensemble of the same classifiers with the processing time. In this paper the ensemble of classifiers had the best results in terms of accuracy, however, it comes to processing time, the decision tree had the best performance.","PeriodicalId":111863,"journal":{"name":"2020 IEEE Latin American GRSS & ISPRS Remote Sensing Conference (LAGIRS)","volume":"22 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2020-03-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"127940415","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2020-03-01DOI: 10.1109/LAGIRS48042.2020.9165682
A. Filho, P. Borba, V. Silva, A. Cerdeira, A. Poz
Quality control (QC) of geospatial data is relevant to urban territorial management to ensure accurate data for government to make strategic decisions when planning cities. The acquisition and control of geospatial data in the Brazilian government must follow INDE – National Data Spatial Infrastructure – through the Technical Specifications. The cadastral cartography from urban areas in Brasilia was updated and divided into 10 areas. Acquired data includes classes, features, attributes and metadata on 1: 1,000 scale. High resolution images and LIDAR data were used to assist the QC process. The first step of the QC was to check positional accuracy. Samples were applied for each class in the mapping block with 4% rate on the feature random selection and all features class had the same level of confidence. Then, three stages were automatically verified: logical consistency, commision and attribute thematic accuracy evaluations. The process also includes the visual interpretation for omission and classification, which involves a certain subjectivity. Everything was executed with QGIS, FME, Erdas Imagine, Postgresql, PostGIS and a plugin specifically developed for that, the DSGTools. The results show that in general, the quantity of errors were low. However, many errors were detected in the elements completeness and thematic accuracy, specially in áreas 1, 2, 3, 6 and 9. In the opposite, the logical consistency and positional accuracy presented the lowest quantity of errors, which does not diminish the relevance of these errors, since it compromises the usability of the data.
{"title":"Quality Control Relevance on Acquisition of Large Scale Geospatial Data to Urban Territorial Management","authors":"A. Filho, P. Borba, V. Silva, A. Cerdeira, A. Poz","doi":"10.1109/LAGIRS48042.2020.9165682","DOIUrl":"https://doi.org/10.1109/LAGIRS48042.2020.9165682","url":null,"abstract":"Quality control (QC) of geospatial data is relevant to urban territorial management to ensure accurate data for government to make strategic decisions when planning cities. The acquisition and control of geospatial data in the Brazilian government must follow INDE – National Data Spatial Infrastructure – through the Technical Specifications. The cadastral cartography from urban areas in Brasilia was updated and divided into 10 areas. Acquired data includes classes, features, attributes and metadata on 1: 1,000 scale. High resolution images and LIDAR data were used to assist the QC process. The first step of the QC was to check positional accuracy. Samples were applied for each class in the mapping block with 4% rate on the feature random selection and all features class had the same level of confidence. Then, three stages were automatically verified: logical consistency, commision and attribute thematic accuracy evaluations. The process also includes the visual interpretation for omission and classification, which involves a certain subjectivity. Everything was executed with QGIS, FME, Erdas Imagine, Postgresql, PostGIS and a plugin specifically developed for that, the DSGTools. The results show that in general, the quantity of errors were low. However, many errors were detected in the elements completeness and thematic accuracy, specially in áreas 1, 2, 3, 6 and 9. In the opposite, the logical consistency and positional accuracy presented the lowest quantity of errors, which does not diminish the relevance of these errors, since it compromises the usability of the data.","PeriodicalId":111863,"journal":{"name":"2020 IEEE Latin American GRSS & ISPRS Remote Sensing Conference (LAGIRS)","volume":"9 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2020-03-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"126752867","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2020-03-01DOI: 10.1109/LAGIRS48042.2020.9165620
E. Ferreira, M. Brito, R. Balaniuk, M. Alvim, J. A. D. Santos
In this work we present BrazilDAM, a novel public dataset based on Sentinel-2 and Landsat-8 satellite images covering all tailings dams cataloged by the Brazilian National Mining Agency (ANM). The dataset was built using georeferenced images from 769 dams, recorded between 2016 and 2019. The time series were processed in order to produce cloud free images. The dams contain mining waste from different ore categories and have highly varying shapes, areas and volumes, making BrazilDAM particularly interesting and challenging to be used in machine learning benchmarks. The original catalog contains, besides the dam coordinates, information about: the main ore, constructive method, risk category, and associated potential damage. To evaluate BrazilDAM’s predictive potential we performed classification essays using state-of-the-art deep Convolutional Neural Network (CNNs). In the experiments, we achieved an average classification accuracy of 94.11% in tailing dam binary classification task. In addition, others four setups of experiments were made using the complementary information from the original catalog, exhaustively exploiting the capacity of the proposed dataset.
{"title":"Brazildam: A Benchmark Dataset For Tailings Dam Detection","authors":"E. Ferreira, M. Brito, R. Balaniuk, M. Alvim, J. A. D. Santos","doi":"10.1109/LAGIRS48042.2020.9165620","DOIUrl":"https://doi.org/10.1109/LAGIRS48042.2020.9165620","url":null,"abstract":"In this work we present BrazilDAM, a novel public dataset based on Sentinel-2 and Landsat-8 satellite images covering all tailings dams cataloged by the Brazilian National Mining Agency (ANM). The dataset was built using georeferenced images from 769 dams, recorded between 2016 and 2019. The time series were processed in order to produce cloud free images. The dams contain mining waste from different ore categories and have highly varying shapes, areas and volumes, making BrazilDAM particularly interesting and challenging to be used in machine learning benchmarks. The original catalog contains, besides the dam coordinates, information about: the main ore, constructive method, risk category, and associated potential damage. To evaluate BrazilDAM’s predictive potential we performed classification essays using state-of-the-art deep Convolutional Neural Network (CNNs). In the experiments, we achieved an average classification accuracy of 94.11% in tailing dam binary classification task. In addition, others four setups of experiments were made using the complementary information from the original catalog, exhaustively exploiting the capacity of the proposed dataset.","PeriodicalId":111863,"journal":{"name":"2020 IEEE Latin American GRSS & ISPRS Remote Sensing Conference (LAGIRS)","volume":"4 3 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2020-03-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"116765590","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2020-03-01DOI: 10.1109/LAGIRS48042.2020.9165650
J. Sartori, J. B. Sbruzzi, E. L. Fonseca
This work aims to define the basic parameters for the automatic mapping of the channel between the Lagoa do Peixe and the Atlantic Ocean, which is located in the municipalities of Tavares and Mostardas, Rio Grande do Sul state, Brazil. The automatic mapping is based on an unsupervised classification of Landsat 8 satellite images at the Google Earth Engine cloud computing platform. The images used were selected to present both channel situations (opened and closed). Three images were selected with acquisition dates that presented the open channel and three that presented the closed channel. Each image was classified using the K-means clustering method, using separately band 6, band 7 (both located at shortwave infrared - SWIR) and the Normalized Difference Water Index (NDWI). Once the number of clusters must be defined a priori by the analyst, as well as the training sample area, these parameters were tested over the dataset and clustering results were compared. All of the generated clusters maps were analyzed over 10 random points, identifying the clustering hits and errors. Due to the absence of reference maps, all the final clustering maps for each date were compared with the composite true color image from the same acquisition date. The NDWI cluster maps showed the best results in separating water and non-water pixels.
这项工作旨在为位于巴西南里奥格兰德州塔瓦雷斯和莫斯塔达斯市的Lagoa do Peixe和大西洋之间的通道自动测绘定义基本参数。自动绘图是基于谷歌地球引擎云计算平台上对Landsat 8卫星图像的无监督分类。所使用的图像被选择来呈现两种通道情况(打开和关闭)。选取三幅图像，采集日期分别为开放通道和封闭通道。每张图像使用K-means聚类方法，分别使用波段6、波段7(均位于短波红外- SWIR)和归一化差水指数(NDWI)进行分类。一旦分析人员必须先验地定义聚类的数量，以及训练样本区域，这些参数将在数据集上进行测试，并比较聚类结果。所有生成的聚类图在10个随机点上进行分析，识别聚类命中和错误。由于缺乏参考地图，每个日期的所有最终聚类地图都与同一采集日期的合成真彩色图像进行比较。NDWI聚类图在分离水像元和非水像元方面效果最好。
{"title":"Preliminary Analysis For Automatic Tidal Inlets Mapping Using Google Earth Engine","authors":"J. Sartori, J. B. Sbruzzi, E. L. Fonseca","doi":"10.1109/LAGIRS48042.2020.9165650","DOIUrl":"https://doi.org/10.1109/LAGIRS48042.2020.9165650","url":null,"abstract":"This work aims to define the basic parameters for the automatic mapping of the channel between the Lagoa do Peixe and the Atlantic Ocean, which is located in the municipalities of Tavares and Mostardas, Rio Grande do Sul state, Brazil. The automatic mapping is based on an unsupervised classification of Landsat 8 satellite images at the Google Earth Engine cloud computing platform. The images used were selected to present both channel situations (opened and closed). Three images were selected with acquisition dates that presented the open channel and three that presented the closed channel. Each image was classified using the K-means clustering method, using separately band 6, band 7 (both located at shortwave infrared - SWIR) and the Normalized Difference Water Index (NDWI). Once the number of clusters must be defined a priori by the analyst, as well as the training sample area, these parameters were tested over the dataset and clustering results were compared. All of the generated clusters maps were analyzed over 10 random points, identifying the clustering hits and errors. Due to the absence of reference maps, all the final clustering maps for each date were compared with the composite true color image from the same acquisition date. The NDWI cluster maps showed the best results in separating water and non-water pixels.","PeriodicalId":111863,"journal":{"name":"2020 IEEE Latin American GRSS & ISPRS Remote Sensing Conference (LAGIRS)","volume":"45 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2020-03-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"114982621","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2020-03-01DOI: 10.1109/LAGIRS48042.2020.9165675
C. Albrecht, N. Bobroff, B. Elmegreen, Marcus Freitag, H. Hamann, Ildar Khabibrakhmanov, Klein Levente, Siyuan Lu, F. Marianno, J. Schmude, X. Shao, Carlo Siebenschuh, Rui Zhang
In this paper we benchmark a previously introduced big data platform that enables the analysis of big data from remote sensing and other geospatial-temporal data. The platform, called IBM PAIRS Geoscope, has been developed by leveraging open source big data technologies (Hadoop/HBase) that are in principle scalable in storage and compute to hundreds of PetaBytes. Currently, PAIRS hosts multiple PetaBytes of curated and geospatial-temporally indexed data. It organizes all data with key-value combinations, performing analytics close to the data to minimize data movement.
{"title":"Pairs (Re)Loaded: System Design & Benchmarking For Scalable Geospatial Applications","authors":"C. Albrecht, N. Bobroff, B. Elmegreen, Marcus Freitag, H. Hamann, Ildar Khabibrakhmanov, Klein Levente, Siyuan Lu, F. Marianno, J. Schmude, X. Shao, Carlo Siebenschuh, Rui Zhang","doi":"10.1109/LAGIRS48042.2020.9165675","DOIUrl":"https://doi.org/10.1109/LAGIRS48042.2020.9165675","url":null,"abstract":"In this paper we benchmark a previously introduced big data platform that enables the analysis of big data from remote sensing and other geospatial-temporal data. The platform, called IBM PAIRS Geoscope, has been developed by leveraging open source big data technologies (Hadoop/HBase) that are in principle scalable in storage and compute to hundreds of PetaBytes. Currently, PAIRS hosts multiple PetaBytes of curated and geospatial-temporally indexed data. It organizes all data with key-value combinations, performing analytics close to the data to minimize data movement.","PeriodicalId":111863,"journal":{"name":"2020 IEEE Latin American GRSS & ISPRS Remote Sensing Conference (LAGIRS)","volume":"5 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2020-03-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"130700213","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2020-03-01DOI: 10.1109/LAGIRS48042.2020.9165655
D. Hoffmeister, M. Herbrecht, Tanja Kramm, P. Schulte
Gypsum-rich material covers the hillslopes above $sim$1000 m of the Atacama and forms the particular landscape. In this contribution, we evaluate random forest-based analysis in order to predict the gypsum distribution in a specific area of-3000 km2, located in the hyperarid core of the Atacama. Therefore, three different sets of input variables were chosen. These variables reflect the different factors forming soil properties, according to digital soil mapping. The variables are derived from indices based on imagery of the ASTER and Landsat-8 satellite, geomorphometric parameters based on the Tandem-X World DE$mathrm{M}^{mathrm{T}mathrm{M}}$, as well as selected climate variables and geologic units. These three different models were used to evaluate the Ca-content derived from soil surface samples, reflecting gypsum content. All three different models derived high values of explained variation ($mathrm{r}^{2}gt$0.886), the RMSE is $sim$4500 mg$cdot kmathrm{g}^{-1}$ and the NRMSE is $sim$6%. Overall, this approach shows promising results in order to derive a gypsum content prediction for the whole Atacama. However, further investigation on the independent variables need to be conducted. In this case, the ferric oxides index (representing magnetite content), slope and a temperature gradient are the most important factors for predicting gypsum content.
富含石膏的材料覆盖了阿塔卡马1000米以上的山坡，形成了独特的景观。在这篇文章中，我们评估了随机森林分析，以预测位于阿塔卡马超干旱核心的3000平方公里特定区域内的石膏分布。因此，我们选择了三组不同的输入变量。根据数字土壤制图，这些变量反映了形成土壤性质的不同因素。变量来源于基于ASTER和Landsat-8卫星影像的指数、基于Tandem-X World DE$mathrm{M}^{mathrm{T}mathrm{M}}$的地貌参数以及选定的气候变量和地质单位。这三种不同的模型被用来评估来自土壤表面样品的钙含量，反映石膏含量。所有三种不同的模型都得到了高解释变异值($ mathm {r}^{2}gt$0.886)， RMSE为$sim$4500 mg$cdot k mathm {g}^{-1}$， NRMSE为$sim$6%。总的来说，这种方法在预测整个阿塔卡马的石膏含量方面显示出很好的结果。但是，需要对自变量进行进一步的调查。在这种情况下，氧化铁指数(代表磁铁矿含量)、坡度和温度梯度是预测石膏含量的最重要因素。
{"title":"Evaluation Of Random Forest–Based Analysis For The Gypsum Distribution In The Atacama Desert","authors":"D. Hoffmeister, M. Herbrecht, Tanja Kramm, P. Schulte","doi":"10.1109/LAGIRS48042.2020.9165655","DOIUrl":"https://doi.org/10.1109/LAGIRS48042.2020.9165655","url":null,"abstract":"Gypsum-rich material covers the hillslopes above $sim$1000 m of the Atacama and forms the particular landscape. In this contribution, we evaluate random forest-based analysis in order to predict the gypsum distribution in a specific area of-3000 km2, located in the hyperarid core of the Atacama. Therefore, three different sets of input variables were chosen. These variables reflect the different factors forming soil properties, according to digital soil mapping. The variables are derived from indices based on imagery of the ASTER and Landsat-8 satellite, geomorphometric parameters based on the Tandem-X World DE$mathrm{M}^{mathrm{T}mathrm{M}}$, as well as selected climate variables and geologic units. These three different models were used to evaluate the Ca-content derived from soil surface samples, reflecting gypsum content. All three different models derived high values of explained variation ($mathrm{r}^{2}gt$0.886), the RMSE is $sim$4500 mg$cdot kmathrm{g}^{-1}$ and the NRMSE is $sim$6%. Overall, this approach shows promising results in order to derive a gypsum content prediction for the whole Atacama. However, further investigation on the independent variables need to be conducted. In this case, the ferric oxides index (representing magnetite content), slope and a temperature gradient are the most important factors for predicting gypsum content.","PeriodicalId":111863,"journal":{"name":"2020 IEEE Latin American GRSS & ISPRS Remote Sensing Conference (LAGIRS)","volume":"9 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2020-03-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"130822012","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2020-03-01DOI: 10.1109/LAGIRS48042.2020.9165649
K. Ferreira, G. R. Queiroz, G. Câmara, R. C. Souza, L. Vinhas, R. F. B. Marujo, R. Simões, C. Noronha, R. W. Costa, J. S. Arcanjo, V. Gomes, M. C. Zaglia
The Brazilian National Institute for Space Research (INPE) produces official information about deforestation as well as land use and cover in the country, based on remote sensing images. The current open data policy adopted by many space agencies and governments worldwide provided access to petabytes of remote sensing images. To properly deal with this vast amount of images, novel technologies have been proposed and developed based on cloud computing and big data systems. This paper describes the INPE’s initiatives in using remote sensing images and cloud services of the Amazon Web Services (AWS) infrastructure to improve land use and cover monitoring.
{"title":"Using Remote Sensing Images and Cloud Services on Aws to Improve Land Use and Cover Monitoring","authors":"K. Ferreira, G. R. Queiroz, G. Câmara, R. C. Souza, L. Vinhas, R. F. B. Marujo, R. Simões, C. Noronha, R. W. Costa, J. S. Arcanjo, V. Gomes, M. C. Zaglia","doi":"10.1109/LAGIRS48042.2020.9165649","DOIUrl":"https://doi.org/10.1109/LAGIRS48042.2020.9165649","url":null,"abstract":"The Brazilian National Institute for Space Research (INPE) produces official information about deforestation as well as land use and cover in the country, based on remote sensing images. The current open data policy adopted by many space agencies and governments worldwide provided access to petabytes of remote sensing images. To properly deal with this vast amount of images, novel technologies have been proposed and developed based on cloud computing and big data systems. This paper describes the INPE’s initiatives in using remote sensing images and cloud services of the Amazon Web Services (AWS) infrastructure to improve land use and cover monitoring.","PeriodicalId":111863,"journal":{"name":"2020 IEEE Latin American GRSS & ISPRS Remote Sensing Conference (LAGIRS)","volume":"16 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2020-03-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"121758679","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2020-03-01DOI: 10.1109/LAGIRS48042.2020.9165591
E. Kaiser, R. Linn, S. Rolim, P. Käfer, N. S. da Rocha, L. R. Diaz, A. Grondona, S. Costa, G. Hallal
The objective of this study was to verify the evolution of surface temperature associated with land use and land cover from 1985 to 2019 in Porto Alegre, RS, Brazil. The methodological procedures were performed in five steps: 1. Definition of the study area; 2. Land use and land cover classification from images of Landsat 5 satellite Thematic Mapper (TM) and Operational Land Imager (OLI) from Landsat 8 satellite; 3. Calculation of surface temperature from TM sensor band 6 and OLI sensor band 10; 4. Analysis of temperature evolution over the historical series; and 5. Temporal relation between surface temperature and land use and land cover classes. The results demonstrated that higher temperatures were associated to the evolution of two classes of land use and land cover: urban area and exposed soil, with the former occupying 31% in 1989 to 75% in 2018 of the study area. When comparing the first and last decade of the historical series for each season, there was an average increase of 4. 18°C in the surface temperature of the districts. Thus, adopting policies that mitigate the effects caused by densification and urban sprawl are necessary, mainly through the conservation of vegetated areas and water reservoirs, as these are crucial for the maintenance of air humidity and evapotranspiration.
{"title":"The Urban Heat Island of Porto Alegre, Rs, Southern Brazil: An Analysis Between 1985 and 2019 Through the Radiative Transfer in the Infrared Thermal.","authors":"E. Kaiser, R. Linn, S. Rolim, P. Käfer, N. S. da Rocha, L. R. Diaz, A. Grondona, S. Costa, G. Hallal","doi":"10.1109/LAGIRS48042.2020.9165591","DOIUrl":"https://doi.org/10.1109/LAGIRS48042.2020.9165591","url":null,"abstract":"The objective of this study was to verify the evolution of surface temperature associated with land use and land cover from 1985 to 2019 in Porto Alegre, RS, Brazil. The methodological procedures were performed in five steps: 1. Definition of the study area; 2. Land use and land cover classification from images of Landsat 5 satellite Thematic Mapper (TM) and Operational Land Imager (OLI) from Landsat 8 satellite; 3. Calculation of surface temperature from TM sensor band 6 and OLI sensor band 10; 4. Analysis of temperature evolution over the historical series; and 5. Temporal relation between surface temperature and land use and land cover classes. The results demonstrated that higher temperatures were associated to the evolution of two classes of land use and land cover: urban area and exposed soil, with the former occupying 31% in 1989 to 75% in 2018 of the study area. When comparing the first and last decade of the historical series for each season, there was an average increase of 4. 18°C in the surface temperature of the districts. Thus, adopting policies that mitigate the effects caused by densification and urban sprawl are necessary, mainly through the conservation of vegetated areas and water reservoirs, as these are crucial for the maintenance of air humidity and evapotranspiration.","PeriodicalId":111863,"journal":{"name":"2020 IEEE Latin American GRSS & ISPRS Remote Sensing Conference (LAGIRS)","volume":"42 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2020-03-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"124743161","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
京公网安备 11010802042870号
京ICP备2023020795号-1
扫码关注我们
求助内容：
应助结果提醒方式：