Figure 2 - uploaded by Sebastian van der Linden
Content may be subject to copyright.
Source publication
The EnMAP-Box is a toolbox that is developed for the processing and analysis of data acquired by the German spaceborne imaging spectrometer EnMAP (Environmental Mapping and Analysis Program). It is developed with two aims in mind in order to guarantee full usage of future EnMAP data, i.e., (1) extending the EnMAP user community and (2) providing ac...
Context in source publication
Context 1
... regard to the large share of ENVI users, the EnMAP-Box is programmed in a way that it can be integrated into the regular ENVI Classic menu (Figure 2). ENVI's available bands list then functions as the file list and users may access the EnMAP-Box applications without leaving their regular IP environment. ...
Citations
... The classifications were conducted using EnMap-Box v3.5. [43,44]. Two supervised machine learning algorithms were applied, namely Random Forest (RF) and Support Vector Machine (SVM). ...
The aim of this study is to predict and map winter wheat yield in the Parvomay municipality, situated in the Upper Thracian Lowland of Bulgaria, utilizing satellite data from Sentinel-2. The main crops grown in the research area are winter wheat, rapeseed, sunflower, and maize. To distinguish winter wheat fields accurately, we evaluated classification methods such as Support Vector Machines (SVM) and Random Forest (RF). These methods were applied to satellite multispectral data acquired by the Sentinel-2 satellites during the growing season of 2020–2021. In accordance with their development cycles, temporal image composites were developed to identify suitable moments when each crop is most accurately distinguished from others. Ground truth data obtained from the integrated administration and control system (IACS) were used for training the classifiers and assessing the accuracy of the final maps. Winter wheat fields were masked using the crop mask created from the best-performing classification algorithm. Yields were predicted with regression models calibrated with in situ data collected in the Parvomay study area. Both SVM and RF algorithms performed well in classifying winter wheat fields, with SVM slightly outperforming RF. The produced crop maps enable the application of crop-specific yield models on a regional scale. The best predictor of yield was the green NDVI index (GNDVI) from the April monthly composite image.
... In this paper, we conducted RF by using ENVI software ( Van der Linden et al. 2015), and all parameters are set as follows: n_ Estimators ¼ 400; Impurity Function: Gini Index; Minimum impurity threshold ¼ 0; and Minimum number of samples ¼ 1. ...
This research aims to quantify the spatial pattern of urban land use/land cover (LULC) change while considering environmental effects. This paper integrates historical Landsat imagery, a remote sensing image processing platform (ENVI), geographical information system (GIS), and socioeconomic data to determine the spatial–temporal urban LULC dynamics and the conversion of LULC in response to the rapid urbanization from 1992 to 2022. Principle component analysis and multiple linear regression are used to determine and model the relationship between the socioeconomic factors and the changes for identifying the driving forces. The results indicate that impervious surfaces have exponentially increased, expanding more than two times from 2,348 to 4,795 km2, in contrast to bare lands, which drastically declined by 95%, from 1,888 to 87 km2. Water bodies have always been relatively fewer, at approximately 100 km2. In addition, the majority of farmland in Jinan City is concentrated in the northern region with a steady area in the range of 2,100–2,900 km2, while the majority of woodland located in the southern region declined from 3,774.52 km2 (37%) to 3,088.28 km2 (30%). Economic development, population growth, and climate change are the primary factors that have an obvious impact on LULC changes.
... We used the Random Forest model to perform classification for all three methods. For the two OBC methods, we employed the RFC in eCognition on the scale of objects, while for the PBC method, we used the RFC tool in ENVI on the scale of pixels [49]. ...
Benggang is a type of erosion landform that commonly occurs in the southern regions of China, posing significant threats to local farmland and human safety. Object-based classification (OBC) can be applied with high-resolution (HR) remote sensing images for detecting Benggang areas on a large spatial scale, offering essential data for aiding in the remediation efforts for these areas. Nevertheless, traditional image segmentation methods may face challenges in accurately delineating Benggang areas. Consequently, the extraction of spatial and textural features from these areas can be susceptible to inaccuracies, potentially compromising the detection accuracy of Benggang areas. To address this issue, this study proposed a novel approach that integrates Segment Anything Model (SAM) and OBC for Benggang detection. The SAM was used to segment HR remote sensing imagery to delineate the boundaries of Benggang areas. After that, the OBC was employed to identify Benggang areas based on spectral, geometrical, and textural features. In comparison to traditional pixel-based classification using the random forest classifier (RFC-PBC) and OBC based on the multi-resolution segmentation (MRS-OBC), the proposed SAM-OBC exhibited superior performance, achieving a detection accuracy of 85.46%, a false alarm rate of 2.19%, and an overall accuracy of 96.48%. The feature importance analysis conducted with random forests highlighted the GLDV Entropy, GLDV Angular Second Moment (ASM), and GLCM ASM as the most pivotal features for the identification of Benggang areas. Due to its inability to extract and utilize these textural features, the PBC yielded suboptimal results compared to both the SAM-OBC and MRS-OBC. In contrast to the MRS, the SAM demonstrated superior capabilities in the precise delineation of Benggang areas, ensuring the extraction of accurate textural and spatial features. As a result, the SAM-OBC significantly enhanced detection accuracy by 34.12% and reduced the false alarm rate by 2.06% compared to the MRS-OBC. The results indicate that the SAM-OBC performs well in Benggang detection, holding significant implications for the monitoring and remediation of Benggang areas.
... The decision tree is a structure of nodes and links between them, where each node has one input and two or more output links to neighboring nodes. Both SVM and RF classifications in this study are implemented using the EnMAP-Box version 3.3 program, 33 which uses the Python machine learning package Scikit-learn. 34 Based on the calculated regression models (Equation 1-3) from the author's previous study, 14 which showed best prediction accuracies according to validation, we computed maps of the predicted LAI, fAPAR, and fCover parameters for the test area. ...
The aim of this study is to map winter wheat fields in designated study area in Bulgaria and to analyze the spatial variation of various biophysical parameters of winter wheat crops in these fields using multispectral satellite imagery. The study uses Sentinel-2 data for image classification and to predict the Leaf Area Index (LAI), fraction of absorbed photosynthetically active radiation (fAPAR), and fraction of vegetation cover (fCover) of the crops. The study area is situated in the Danubian plain in Bulgaria, a heavily cultivated agricultural region in Europe. To distinguish winter wheat fields from other agricultural fields, classification techniques were applied using two methods, Support Vector Machines (SVM) and Random Forest (RF), to identify the winter wheat fields in different phonological phases during the growing season. Both classification methods performed with similar accuracy and showed high accuracies in classifying winter wheat using Sentinel-2 images at various phonological phases (F1 > 93%; tillering; F1 > 95%; stem elongation; F1 > 94%; anthesis). To predict the LAI, fAPAR, and fCover dynamics in the winter wheat fields, regression models were used, calibrated with vegetation indices and in situ data. Maps displaying the within-field variation of LAI, fAPAR, and fCover were created for two growth stages: tillering and stem elongation.
... Another very useful plugin was EnMAP-Box, developed by the Humboldt University of Berlin and the University of Greifswald, to handle data from the German hyperspectral satellite EnMAP [54]. This plugin constituted the starting point for the development of the AVHYAS plugin mentioned above. ...
... The main objective was to improve the ability to distinguish between bare soil and temporary or permanent vegetation by photointerpretation. The selection of the bands is based on the combination method of the raster layer styling panel of the Qgis EnMAP-Box plugin [54]. Table 4 shows the RGB bands used for each composition, and Figure 3 shows the resulting maps. ...
Hyperspectral satellite missions, such as PRISMA of the Italian Space Agency (ASI), have opened up new research opportunities. Using PRISMA data in land cover classification has yet to be fully explored, and it is the main focus of this paper. Historically, the main purposes of remote sensing have been to identify land cover types, to detect changes, and to determine the vegetation status of forest canopies or agricultural crops. The ability to achieve these goals can be improved by increasing spectral resolution. At the same time, improved AI algorithms open up new classification possibilities. This paper compares three supervised classification techniques for agricultural crop recognition using PRISMA data: random forest (RF), artificial neural network (ANN), and convolutional neural network (CNN). The study was carried out over an area of 900 km2 in the province of Caserta, Italy. The PRISMA HDF5 file, pre-processed by the ASI at the reflectance level (L2d), was converted to GeoTiff using a custom Python script to facilitate its management in Qgis. The Qgis plugin AVHYAS was used for classification tests. The results show that CNN gives better results in terms of overall accuracy (0.973), K coefficient (0.968), and F1 score (0.842).
... An RF algorithm was selected for all experiments involved in the SVI evaluation because of its excellent performance in high-dimensional data classification and feature importance ranking. The classification and feature ranking tool was EnMAP-Box [55]. When the tree species classification using the abovementioned feature sets was completed, the importance of features in the MFSs + SVIs was measured, and the OFSs for each MFS + SVI were obtained. ...
To fully mine information regarding differences among various tree species from remote sensing data and improve the accuracy of tree species recognition, this study utilized the spectral reflection value, wavelength, and time as parameters and employed three algorithms to create an expression for the spectral volume index (SVI). Then, data were obtained by applying RedEdge-MX to four phases, SVI features were extracted, and a mixed feature set of spectral band + texture + digital surface model + SVI was constructed. A random forest algorithm was employed to determine the importance of the SVI features and derive the optimal feature set for tree species classification. The additional objectives were to determine if the SVI features have an active role in tree species classification and which algorithm is more conducive for extracting useful SVI features. The SVI features extracted with volume constraints exhibit better performance in tree species recognition than those extracted without volume constraints. Moreover, the SVI features extracted using a variable-constrained volume were better than those extracted using a constant-constrained volume. The combination of SVI features could improve the accuracy of tree species recognition (the highest overall accuracy was 92.76%), but the improvement effect was limited (the value was 92.16% when SVI features were not combined). These findings show that the SVI obtained using this method could be used to mine the difference information of tree species in images to a certain extent and hence, could be used in tree species identification.
... A general near data processing framework proposed in the literature. It does not need to change the existing hardware structure, can optimize different data processing applications, and has high versatility (Linden et al. 2015). Biscuit implements a C?? function library on the storage device and the host, which runs in the host side program and SSD side module, respectively. ...
One of the key components of artificial intelligence algorithms is machine learning, involving a variety of fields, and has been applied in many artificial intelligence systems, including computer vision algorithm, radio network algorithm, medical diagnosis algorithm and intelligent robot system algorithm. In the form of machine learning algorithm, the machine learning module of the algorithm is first used to calculate the consumption, the main performance modules are optimized and improved, and the system data under database optimization are obtained, and selected the optimized structure of the database for calculation, data analysis for the calculation results. Finally, in the design of the database optimization system, the separation of the database system storage engine is studied, and the database optimization form under the data processing structure is proposed. In terms of performance and functionality and reliability, it helps to solve the loss problem caused by big data processing in transmission. In the research of data intensive downward moving calculation process, the optimized solution of data processing is estimated. The results show that using computer terminal sampling comparison to select the executable data processing scheme. The result of this paper shows that it can improve the calculation efficiency of data optimization system query.
... It has been successfully applied to map tree species (Dalponte et al., 2013;Ghosh and Joshi, 2014;Cavallaro et al., 2015), hence this method was preferred in this study. Random Forest classification implemented in EnMAP-Box (van der Linden et al., 2015) was used. The classification model was computed using 500 decision trees, gini coefficient as the impurity function and stopping criteria of 1 for minimum number of samples in a node and 0 as minimum impurity. ...
... Inter-elemental correlations with Pearson R for rock/soil and foliar chemical concentrations are shown in Figure S4. The low to moderate correlation is not unexpected, other studies have also presented that elemental concentrations between soil and plant samples do not exactly co-vary, due to chemical and biological factors, such as variations in pH and bacterial richness, as well as temperature differences (Borovička et al., 2006;Shtangeeva et al., 2011;Crowther et al., 2019;Sleimi et al., 2021;Ubeynarayana et al., 2021). Furthermore, the element uptake rates can vary amongst plant species and are dependant on their broader environment such as the soil pH (e.g. ...
Hyperspectral remote sensing is an emerging technique to develop new cost- and time-effective geophysical mapping methods. To overcome challenges introduced by plant cover in geothermal systems globally, we hypothesise that foliage can be used as a proxy to map underlying surface geothermal activity and heat-flux due to their capability on elemental uptake from geothermal fluids and host rock/soil. This study shows for the first time that foliar elemental mapping can be used to image geothermal systems using both high-resolution airborne and satellite hyperspectral images.
This study has specifically targeted kanuka shrub (kunzea ericoides var. microflora) as a proxy media to develop air- and spaceborne hyperspectral solutions to monitor inaccessible, biologically and culturally sensitive geothermal areas. Using high resolution airborne AisaFENIX and PRISMA hyperspectral data, foliar element maps for Ag, As, Ba and Sb have been developed using Kernel Partial Least Squares Regression and Random Forest classification models to track their foliar distribution and develop a conceptual model for metal and thermal induced changes in plants. Our study shows evidence that the created foliar element maps are in concordance with independent LiDAR-retrieved canopy structure and height as well as temperature effects of the underlying geothermal field. This study has proven air- and spaceborne hyperspectral sensors can indeed capture critical information within the VNIR and SWIR regions (e.g. ∼452, ∼500, ∼670, ∼820, ∼970, ∼1180, ∼1400 and ∼2000 nm) that can be used to identify metal and thermal-induced spectral changes in plants reliably (overall accuracy of 0.41–0.66) with remotely sensed imagery. Our non-invasive method using hyperspectral remote sensing can complement existing practices for exploration and management of renewable geothermal resources through timely monitoring from air- and spaceborne platforms.
... Radiometric cor-rection includes the removal of spectrally overlapping bands, bad band detection, and reductions for dead pixel and erroneous detector columns. An implementation of MOD-TRAN LUT based radiative transfer modeling proposed by [47] and originally designed for the EnMAP-Box [48] was used for the correction of atmospheric influence. It includes Aerosol Optical Thickness (AOT) and Columnar Water Vapor (CWV) retrieval as well as spectral Smile and adjacency correction [49]. ...
Remote sensing and soil spectroscopy applications are valuable techniques for soil property estimation. Soil organic matter (SOM) and calcium carbonate are important factors in soil quality, and although organic matter is well studied, calcium carbonates require more investigation. In this study, we validated the performance of laboratory soil spectroscopy for estimating the aforementioned properties with referenced in situ data. We also examined the performance of imaging spectroscopy sensors, such as the airborne HySpex and the spaceborne PRISMA. For this purpose, we applied four commonly used machine learning algorithms and six preprocessing methods for the evaluation of the best fitting algorithm.. The study took place over crop areas of Amyntaio in Northern Greece, where extensive soil sampling was conducted. This is an area with a very variable mineralogical environment (from lignite mine to mountainous area). The SOM results were very good at the laboratory scale and for both remote sensing sensors with R2 = 0.79 for HySpex and R2 = 0.76 for PRISMA. Regarding the calcium carbonate estimations, the remote sensing accuracy was R2 = 0.82 for HySpex and R2 = 0.36 for PRISMA. PRISMA was still in the commissioning phase at the time of the study, and therefore, the acquired image did not cover the whole study area. Accuracies for calcium carbonates may be lower due to the smaller sample size used for the modeling procedure. The results show the potential for using quantitative predictions of SOM and the carbonate content based on soil and imaging spectroscopy at the air and spaceborne scales and for future applications using larger datasets.
... For each site, orthophotographs (with a 0.5-m digital resolution) were first segmented using the segment mean shift algorithm (ArcMap v.10.5.1) to group contiguous close mean value pixels in the same segment. A supervised classification based on the random forest algorithm was then applied to these segmented images using the EnMAP-Box toolbox (Breiman 2001;Van der Linden et al. 2015;EnMAP-Box Developers, 2019) based on the scikit-learn Python library (Pedregosa et al. 2011). Accuracy values were computed based on confusion matrices from a sample of 500 random points for each year and each department (Table 1). ...
ContextTreeline-ecotone spatial patterns and their dynamics reflect underlying processes. Changes in ecotone pattern may reflect changes in natural drivers or land-use practices. However, characterizing these dynamics presents a major challenge, limiting our ability to map, understand and predict changes in the upper limits of mountain forests.Objective
This paper proposes a new method using multiple pattern dimensions to describe treeline-ecotone spatial pattern shifts. This standardized protocol should be able to (i) distinguish different types of treeline-ecotone patterns within a large study area, (ii) characterize temporal pattern shifts in spatial pattern between two or more dates.Method
We mapped alpine treeline ecotones (ATE) at 648 sites in the eastern French Pyrenees using aerial images from ~ 1955 and ~ 2015, identifying forest and non-forest areas at the hillslope scale. Extracted patch metrics were summarized using a Principle Component Analysis (PCA) and spatial pattern change was quantified from the shift in the PCA space and compared to elevational shifts.ResultsThree clusters of patterns were distinguished: diffuse, discrete and island-forming ATEs. Between 1955 and 2015, about half of the sites changed from one pattern cluster to another. Shifts into discrete ATEs were associated with smaller and negative elevational shifts, while shifts into diffuse ATEs coincided with the highest positive elevational shifts.Conclusion
The proposed method allows a standardized and repeatable quantification of vegetation pattern change in alpine treeline ecotones based on historical aerial imagery. Seeing the importance of treeline-ecotone shifts for alpine biodiversity, we encourage the use of this protocol to better understand treeline dynamics at treelines globally.
