Earth Sensor Research Articles

Spectral response of forest disturbances induced by beaver caused floods: A case study in Estonia using Sentinel-2 MSI image time series

Beavers are known as ecosystem engineers and the habitats that they create can change the landscape greatly. When a new beaver colony establishes itself by building dams, digging canals and burrows and felling trees, the resulting changes are often large enough to be studied with medium resolution earth observation sensors like Sentinel-2 MSI. In this study we compare the spectral signatures of 405 sample areas disturbed by beaver-induced flooding with 261 healthy forest sample areas surrounding the area. We used 28 Sentinel-2 MSI multispectral images from years 2015 to 2018 over the southern part of Estonia in Military Grid Reference System map tile T35VME. In summer the average pixel values for areas that are affected by beavers show the largest differences in reflectance values for shortwave infrared (SWIR) and the visible parts of the spectrum compared to areas that are not affected by beavers. Some smaller differences are present also in the near-infrared (NIR) parts of the spectrum, but sometimes they are not significant according to p-values, being over the 0.05 threshold, of the t-test. In autumn and spring, when deciduous trees do not have their leaves and ground vegetation is not thriving, the differences in visible parts of the spectrum disappear. Multispectral vegetation indices, like the Normalized Difference Vegetation Index (NDVI) and others, also show clear differences in the beaver-disturbed forests and surrounding healthy forests throughout all vegetation phenology stages. Keywords: beavers; flood disturbance; phenology; forest damage; habitat change; Sentinel-2 MSI

Summer School on Earth Sensing 2025

Summer School on Earth Sensing 2025

Machine Learning and New-Generation Spaceborne Hyperspectral Data Advance Crop Type Mapping

Hyperspectral sensors provide near-continuous spectral data that can facilitate advancements in agricultural crop classification and characterization, which are important for addressing global food and water security issues. We investigated two new-generation hyperspectral sensors, Germany’s Deutsches Zentrum für Luft‐ und Raumfahrt Earth Sensing Imaging Spectrometer (DESIS) and Italy’s PRecursore IperSpettrale della Missione Applicativa (PRISMA), within California???s Central Valley in August 2021 focusing on five irrigated agricultural crops (alfalfa, almonds, corn, grapes, and pistachios). With reference data from the U.S. Department of Agriculture Cropland Data Layer, we developed a spectral library of the crops and classified them using three machine learning algorithms (support vector machines [SVM], random forest [RF], and spectral angle mapper [SAM]) and two philosophies: 1. Full spectral analysis (FSA) and 2. Optimal hyperspectral narrowband (OHNB) analysis. For FSA, we used 59 DESIS four-bin product bands and 207 of 238 PRISMA bands. For OHNB analysis, 9 DESIS and 16 PRISMA nonredundant OHNBs for studying crops were selected. FSA achieved only 1% to 3% higher accuracies relative to OHNB analysis in most cases. SVM provided the best results, closely followed by RF. Using both DESIS and PRISMA image OHNBs in SVM for classification led to higher accuracy than using either image alone, with an overall accuracy of 99%, producer’s accuracies of 94% to 100%, and user???s accuracies of 95% to 100%.

Satellite position and attitude estimation using an infrared earth sensor

Micro/nano-satellites are constrained by payload, size, and cost, making enhancements in design flexibility crucial, particularly for orbit and attitude determination systems. An effective strategy is the innovative utilization of existing sensors. This study investigates a novel application of Earth sensors for autonomous position and attitude determination enabling them as a viable option for autonomous navigation in low-cost micro/nano-satellites through computer vision technology. To address large resolution differences and distortions between sensed infrared images and reference maps, this paper presents a coarse-to-fine matching framework that integrates deep learning features and area-based registrations. First, CNN-based registration and optimization techniques are utilized for coarse registration. A modified VGG16 (M-VGG) and a multiscale pyramid information fusion (MPIF) module are employed to extract and describe deep abstract features, enhancing robustness. Subsequently, edge-based extended phase correlation is employed for fine registration. Finally, the ultimate position and attitude parameters are determined by integrating the results from coarse and fine registration. The effectiveness of the proposed scheme is validated using synthetic images. An analysis of 342 images demonstrates sub-pixel registration accuracy, with a root mean square error (RMSE) of 1.9322 km for position and 0.1185° for attitude.

Performance Estimation of a Medium-Resolution Earth Observation Sensor Using Nanosatellite Replica.

In many areas of engineering, the design of a new system usually involves estimating performance-related parameters from early stages of the project to determine whether a given solution will be compliant with the defined requirements. This aspect is particularly relevant during the design of satellite payloads, where the target environment is not easily accessible in most cases. In the context of Earth observation sensors, this problem has been typically solved with the help of a set of complex pseudo-empirical models and/or expensive laboratory equipment. This paper describes a more practical approach: the illumination conditions measured by an in-orbit payload are recreated on ground with the help of a replica of the same payload so the performance of another Earth observation sensor in development can be evaluated. The proposed method is specially relevant in the context of small satellites, as the possibility of having extra units devoted to these tasks becomes greater as costs are reduced. The results obtained using this method in an actual space mission are presented in this paper, giving valuable information that will help in further stages of the project.

GEOSatDB: global civil earth observation satellite semantic database

ABSTRACT Satellite remote sensing, characterized by extensive coverage, frequent revisits, and continuous monitoring, provides essential data support for addressing global challenges. Over the past six decades, thousands of Earth observation satellites and sensors have been deployed worldwide. These valuable Earth observation assets are contributed independently by various nations and organizations employing diverse methodologies. This poses a significant challenge in effectively discovering global Earth observation resources and realizing their full potential. In this paper, we describe the development of GEOSatDB, the most complete semantic database of civil Earth observation satellites developed based on a unified ontology model. A similarity matching method is used to integrate satellite information and a prompt strategy is used to extract unstructured sensor information. The resulting semantic database contains 127,949 semantic statements for 2,340 remote sensing satellites and 1,021 observation sensors. The global Earth observation capabilities of 195 countries worldwide have been analyzed in detail, and a concrete use case along with an associated query demonstration is presented. This database provides significant value in effectively facilitating the semantic understanding and sharing of Earth observation resources.

Satellite Hyperspectral Nighttime Light Observation and Identification with DESIS

The satellite imagery of nighttime lights (NTLs) has been studied to understand human activities, economic development, and more recently, the ecological impact of brighter night skies. The Visible Infrared Imaging Radiometer Suite (VIIRS) Day–Night Band (DNB) offers perhaps the most advanced nighttime imaging capabilities to date, but its large pixel size and single band capture large-scale changes in NTL while missing granular but important details, such as lighting type and brightness. To better understand individual NTL sources in a region, the spectra of nighttime lights captured by the DLR Earth Sensing Imaging Spectrometer (DESIS) were extracted and compared against near-coincident VIIRS DNB imagery. The analysis shows that DESIS’s finer spatial and spectral resolutions can detect individual NTL locations and types beyond what is possible with the DNB. Extracted night light spectra, validated against ground truth measurements, demonstrate DESIS’s ability to accurately detect and identify narrow-band atomic emission lines that characterize the spectra of high-intensity discharge (HID) light sources and the broader spectral features associated with different light-emitting diode (LED) lights. These results suggest the possible application of using hyperspectral data from moderate-resolution sensors to identify lamp construction details, such as illumination source type and light quality in low-light contexts. NTL data from DESIS and other hyperspectral sensors may improve the scientific understanding of light pollution, lighting quality, and energy efficiency by identifying, evaluating, and mapping individual and small groups of light sources.

Multi-User System for Earth Sensing Spacecraft Attitude Calibration and Analysis

The Teledyne Multiple User System for Earth Sensing (“MUSES”) was developed for commercial Earth imaging and instrument technology development on the International Space Station (ISS). MUSES simultaneously hosts up to four Earth ensing instruments and provides inertial pointing and tracking to orient instruments toward planned targets on the ground. Up to four instruments are robotically installed on MUSES and periodically interchanged as warranted. MUSES was delivered to the ISS in June 2017, with initial testing successfully completed and subsequently documented in an initial requirements verification report. Assessing the performance of the MUSES attitude estimation system is challenging due to the lack of an independent attitude estimate of the platform attitude. A novel approach is introduced herein where the ISS attitude estimate, derived from ISS Global Positioning System sensors, is employed as an independent measure of MUSES platform attitude. Spectral decomposition methods are used to account for the contributions of ISS deformations to the variance in disparities between the ISS and MUSES attitudes and thus enable a less conservative estimate of the variance in MUSES attitude error. Implementing the spectral decomposition results in a best estimate upper bound on MUSES attitude errors of 34.5 and 27.7 arcsec, respectively, in the along-track and cross-track axes. Both the simulated and real results obtained from the spacecraft are presented.

Intercomparison of Landsat OLI and JPSS VIIRS Using a Combination of RadCalNet Sites as a Common Reference

Independent radiometric data collected from multiple ground sites as part of vicarious calibration activities can be combined to harmonize the data products of Earth observation sensors with different temporal, spectral, and spatial resolutions. Recent coordinated international efforts for open fiducial reference measurements have provided the worldwide user community with new ways to explore the calibration and harmonization of data produced by the sensors. To be correct, the results from each ground system must be traceable to the same well-understood standard system, and ideally to the international system of units (SI). Additionally, the calibration test site should be homogeneous over an area larger than the spatial resolutions of each sensor, so that ground measurements are representative of the area seen by the sensors being calibrated. Here, we use a combination of independent and SI-traceable radiometric data provided from two sites of the Radiometric Calibration Network (RadCalNet) to compare the radiometric response of sensors with different spectral and spatial resolutions that operate on different orbits. These sensors are Operational Land Imagers (OLI) of the Landsat-8 and Landsat-9 missions, and Visible Infrared Imaging Radiometer Suites (VIIRS) of the Suomi-National Polar-Orbiting Operational Environmental Satellite System Preparatory Project (SNPP) and Joint Polar Satellite System-1 (JPSS-1) missions. The sensor radiometric responses are compared via temporal averaging of the ratios of top-of-atmosphere reflectance values for each sensor to those reported by RadCalNet. Our intercomparison results show that these on-orbit sensors are calibrated within their absolute radiometric uncertainties. The absolute radiometric uncertainties of single-sensor over single-site intercomparisons at 550 nm is between 5% and 6%. Having the opportunity to look at the intercomparison results of Landsat-9 OLI compared to each calibration site individually and then in combination allowed us to investigate potential systematic site-dependent biases. We did not observe significant site-dependent biases in the behavior of the four on-orbit sensors compared to the calibration sites. The absolute radiometric uncertainty of a single sensor over multiple-site intercomparisons at 550 nm is 5.4%. We further investigated site-dependent biases by looking at the double-ratio calibration coefficients of the on-orbit sensors, calculated with reference to those sites.

Uncovering the hidden: Leveraging sub-pixel spectral diversity to estimate plant diversity from space

Remotely sensed spectral diversity has emerged as a promising proxy for plant diversity. However, spectral diversity approaches relate image spectra to plant community diversity by only incorporating variation among adjacent pixels, considering each pixel as a homogeneous entity composed of one class, and disregarding the within-pixel variability. Although such approaches might work for remotely-sensed data with fine spatial resolution, they might not be viable solutions to estimate plant diversity using coarse-resolution data from forthcoming spaceborne imagers. To address the limitations associated with spectral diversity approaches, we proposed a novel approach, known as endmember diversity, for remote estimation of plant diversity through quantifying spectral diversity at the sub-pixel level and taking into account the within-pixel variability. The approach consisted of deriving the number and abundance of distinct spectral entities within each pixel via spectral unmixing. In doing so, we considered the spectral signature of each pixel as a mixture of distinct spectral entities, commonly known as endmembers. We then used the per-pixel endmembers and their abundance to calculate different spectral diversity metrics for every pixel. We assessed the performance of the endmember diversity approach at estimating plant taxonomic and phylogenetic diversity based on two experiments using a simulated spectral dataset and a real-world spaceborne DESIS (DLR Earth Sensing Imaging Spectrometer) dataset. In both experiments, we found significant associations between endmember diversity and in situ plant diversity. Additionally, our method applied to DESIS data outperformed a conventional spectral diversity metric based on the coefficient of variation when applied to 1-m airborne imaging spectroscopy data. Collectively, our results demonstrate the capability of forthcoming spaceborne imagers to monitor local plant diversity.

Calibration of the SNPP and NOAA 20 VIIRS sensors for continuity of the MODIS climate data records

Accurate long-term sensor calibration and periodic re-processing to ensure consistency and continuity of atmospheric, land and ocean geophysical retrievals from space within the mission period and across different missions is a major requirement of climate data records. In this work, we applied the Multi-Angle Implementation of Atmospheric Correction (MAIAC)-based vicarious calibration technique over Libya-4 desert site to perform calibration analysis of Visible Infrared Imaging Radiometer Suite (VIIRS) on Suomi National Polar-orbiting Partnership (SNPP) and NOAA-20 satellites. For both VIIRS sensors we characterized residual linear calibration trends and cross-calibrated both sensors to MODerate resolution Imaging Spectroradiometer (MODIS) Aqua regarded as a calibration standard. The relative spectral response (RSR) differences were accounted for using the German Aerospace Center (DLR) Earth Sensing Imaging Spectrometer (DESIS) hyperspectral surface reflectance data. Our results agree with independent vicarious calibration results of both the MODIS/VIIRS Characterization Support Team as well as the CERES Imager and Geostationary Calibration Group within estimated uncertainty of 1–2%. Analysis of MAIAC geophysical products with the new calibration shows a high level of agreement of MAIAC aerosol, surface reflectance and NDVI records between MODIS and VIIRS. Excluding high aerosol optical depth (AOD), all three sensors agree in AOD with mean difference (MD) less than 0.01 and residual mean squared difference rmsd ∼ 0.04. Spectral geometrically normalized surface reflectance agrees within rmsd of 0.003–0.005 in the visible and 0.01–0.012 at longer wavelengths. The residual surface reflectance differences are fully explained by differences in spectral filter functions. Finally, difference in NDVI is characterized by rmsd ∼ 0.02 and MD less than 0.003 for NDVI based on VIIRS imagery bands I1/I2 and less than 0.01 for NDVI based on VIIRS radiometric bands M5/M7. In practical sense, these numbers indicate consistency and continuity in MAIAC records ensuring the smooth transition from MODIS to VIIRS.

Strategies for improving the communication of satellite-derived InSAR data for geohazards through the analysis of Twitter and online data portals

Abstract. Satellite-based earth observation sensors are increasingly able to monitor geophysical signals related to natural hazards, and many groups are working on rapid data acquisition, processing, and dissemination to data users with a wide range of expertise and goals. A particular challenge in the meaningful dissemination of Interferometric Synthetic Aperture Radar (InSAR) data to non-expert users is its unique differential data structure and sometimes low signal-to-noise ratio. In this study, we evaluate the online dissemination of ground deformation measurements from InSAR through Twitter, alongside the provision of open-access InSAR data from the Centre for Observation and Modelling of Earthquakes, Volcanoes and Tectonics (COMET) Looking Into Continents from Space with Synthetic Aperture Radar (LiCSAR) processing system. Our aim is to evaluate (1) who interacts with disseminated InSAR data, (2) how the data are used, and (3) to discuss strategies for meaningful communication and dissemination of open InSAR data. We found that the InSAR Twitter community was primarily composed of non-scientists (62 %), although this grouping included earth observation experts in applications such as commercial industries. Twitter activity was primarily associated with natural hazard response, specifically following earthquakes and volcanic activity, where users disseminated InSAR measurements of ground deformation, often using wrapped and unwrapped interferograms. For earthquake events, Sentinel-1 data were acquired, processed, and tweeted within 4.7±2.8 d (the shortest was 1 d). Open-access Sentinel-1 data dominated the InSAR tweets and were applied to volcanic and earthquake events in the most engaged-with (retweeted) content. Open-access InSAR data provided by LiCSAR were widely accessed, including automatically processed and tweeted interferograms and interactive event pages revealing ground deformation following earthquake events. The further work required to integrate dissemination of InSAR data into longer-term disaster risk-reduction strategies is highly specific, to both hazard type and international community of practice, as well as to local political setting and civil protection mandates. Notably, communication of uncertainties and processing methodologies are still lacking. We conclude by outlining the future direction of COMET LiCSAR products to maximize their useability.

Research on small-sized earth pressure sensor based on ultra-weak fiber Bragg grating

Research on small-sized earth pressure sensor based on ultra-weak fiber Bragg grating

Laboratory Test Study on Pile Jacking Penetration Mechanism Considering Different Diameter and Length Based on Photoelectric Integration Technology

Model tests are carried out on the jacked single piles of different diameters and pile lengths under the model pile of different diameters and pile lengths in clayey soil, which aims to investigate the penetration mechanical mechanism. How to accurately test the pile end resistance and pile side resistance during jacked pile sinking is particularly important. In this paper, a full-section spoke-type pressure sensor, a double diaphragm temperature self-compensating fiber Bragg grating (FBG) earth pressure sensor and a sensitized miniature FBG strain sensor are jointly applied to a single pile penetration model test to test a single pile driving force, pile end resistance and pile body stress during penetration. The test results show that the load transfer performance of test piles will be affected by different diameters, and the axial force transfer capability of a large diameter in the depth direction is better than that of a small diameter since the compacting effect is more obvious. The unit skin friction of the pile increases gradually as the depth increases, which is larger due to the lateral extrusion force increasing as the diameter increases. At the same depth, the unit skin friction of two different diameter piles demonstrates “friction fatigue”, which also decreases obviously as the depth increases. Under the conditions of this test, the maximum frictional resistance of the pile TP1 pile side is about 27.7% higher than that of the test pile TP2. In the static pile sinking process of three test piles in cohesive soil, 50% is end bearing; therefore, there is 50% friction, and the diameter influences the end bearing and the length influences the friction.

Towards developing comparable optical and SAR remote sensing inundation mapping with hydrodynamic modelling

ABSTRACT Inundation mapping is an essential part of environmental monitoring, flood disaster management and risk mitigation. There are many earth observation sensors that can provide spatial information about inundation extent at different times. However, these extents need to be comparable to provide an accurate and consistent estimate of a flood’s progression. Monitoring inundation extent around the peak of a flood event is important because it captures the hazardous period during a large flood event, and it identifies connections between off-stream waterholes and flood waters for environmental monitoring. This paper presents results from a study comparing near-coincident flood inundation maps derived from optical (Landsat, MODIS, Sentinel-2 and VIIRS) and Synthetic Aperture Radar (SAR) (Sentinel-1 and NovaSAR-1) remote sensing imagery. We also compare all inundation maps derived from remote sensing data with near-coincident hydrodynamic (HD) modelling. The study was conducted for the Fitzroy floodplain in Western Australia, a large, complex and remotely located river basin. The results show that optical remote sensing data have average F1 scores ranging from 0.57 to 0.65 when compared to the HD model results, with Landsat and MODIS performing best. Sentinel-1 and NovaSAR-1 SAR have a poor agreement (average F1 score of 0.31 and 0.35 respectively) when compared to the HD model results, particularly within scattered vegetation adjacent to the river channel, with better results in open water on the floodplain and in the river. If comparisons are made only during the peak flood stage, the F1 scores improve for the optical data (0.61 up to 0.8). Comparisons of the remote sensing inundation maps show that the optical data are suitable for interchangeable mapping during large flood events.

Determination of Bayesian Cramér–Rao Bounds for Estimating Uncertainties in the Bio-Optical Properties of the Water Column, the Seabed Depth and Composition in a Coastal Environment

The monitoring of coastal areas using remote sensing techniques is an important issue to determine the bio-optical properties of the water column and the seabed composition. New hyperspectral satellite sensors (e.g., PRISMA, DESIS or EnMap) are developed to periodically observe ecosystems. The uncertainties in the retrieved geophysical products remain a key issue to release reliable data useful for the end-users. In this study, an analytical approach based on Information theory is proposed to investigate the Cramér–Rao lower Bounds (CRB) for the uncertainties in the ocean color parameters. Practically, during the inversion process, an a priori knowledge on the estimated parameters is used since their range of variation is supposed to be known. Here, a Bayesian approach is attempted to handle such a priori knowledge. A Bayesian CRB (BCRB) is derived using the Lee et al. semianalytical radiative transfer model dedicated to shallow waters. Both environmental noise and bio-optical parameters are supposed to be random vectors that follow a Gaussian distibution. The calculation of CRB and BCRB is carried out for two hyperspectral images acquired above the French mediterranean coast. The images were obtained from the recently launched hyperspectral sensors, namely the DESIS sensor (DLR Earth Sensing Imaging Spectrometer, German Aerospace Center), and PRISMA (Precursore IpperSpettrale della Mission Applicativa—ASI, Italian Space Adjency) sensor. The comparison between the usual CRB approach, the proposed BCRB approach and experimental errors obtained for the retrieved bathymetry shows the better ability of the BCRB to determine minimum error bounds.

Potential of DESIS and PRISMA hyperspectral remote sensing data in rock classification and mineral identification:a case study for Banswara in Rajasthan, India.

Remote sensing datasets and methods are suitable for mapping and managing the natural resources like minerals, clean water, and energy and also govern their sustainability nowadays. Hyperspectral (HS) imaging has immense potential for rock type classification, mineral mapping, and identification. This work demonstrates the potential of feature extraction techniques and unsupervised machine learning methods for the space-borne hyperspectral remote sensing data in characterizing and identifying mineral and classifying rock type in Banswara, Rajasthan, India. Feature extraction techniques can reveal variations within the data, which can help identify geological areas, reduce noise, and check the dimensionality of the data. Singular value decomposition (SVD)-based principal component analysis (PCA), kernel PCA (KPCA), minimum noise fraction (MNF), and independent component analysis (ICA) were tested for lithological mapping using recently launched DLR Earth Sensing Imaging Spectrometer Hyperspectral (DESIS) and PRecursore IperSpettrale della Missione Applicativa (PRISMA) data in order to map geologically significant areas. Unsupervised machine learning methods, such as Iterative Self-Organizing Data Analysis Technique (ISODATA) and K-means, were also employed. Vertex component analysis (VCA) was utilized to check for similarity and identify various spectral features. Our work demonstrates the advantages of using feature extraction algorithms such as PCA and KPCA over MNF and ICA in geological mapping and interpretability. We recommend K-means as the preferred method for lithological classification of hyperspectral remote sensing data. Our work highlights the potential of advanced feature extraction algorithms for mineral mapping using hyperspectral data, providing different ways to identify minerals and ultimately leading to better mineral resource management.

Evaluation of surface reflectance bandpass adjustment techniques

There is an increasing number of on-orbit earth observation sensors in the solar domain (visible to middle infrared). While most the sensors are designed with apparent analogous bandpasses, they often exhibit differences in terms of Relative Spectral Response (RSR). Although the differences are well characterized, there is a need for techniques to adjust for the effect of these differences on surface reflectance after accounting for calibration, directional, and atmospheric effects. This research evaluated eight bandpass adjustment techniques using synthetic and actual remote sensing observations on seven widely used sensors. The scope of the study is global.The eight evaluated techniques were: a) spectral band adjustment factor technique (SBAF, i.e., one-coefficient regression), b) linear fit technique (i.e., two-coefficient regression), c) three Adaptive SBAF techniques (ASBAF), which are defined according to three different cost functions and apply a target-dependent SBAF, d) two artificial neural network approaches using (i) a single band (ANN-1B) and (ii) all bands (ANN-NB) as inputs, and e) a Classification and Regression Tree method (CART) using all bands as inputs. All these techniques require a calibration phase, which was carried out separately using three hyperspectral data sets: (i) USGS spectral measurements, (ii) simulated reflectance by the ProSail radiative transfer model, and (iii) real-world Hyperion observations. The full data set is publically available.The evaluation using the three hyperspectral data sets alone showed that the techniques with a single band as input (SBAF, LIN, and ANN-1B) generated higher uncertainty than the techniques with all bands as input (ASBAF, ANN-N, CART). The ASBAF techniques performed well with a few differences among the three ASBAF variants. The ANN-N was the technique that performed the best. The evaluation based on actual remote sensing data sets (Landsat-8 and Sentinel-2 data were used) suggested that all techniques reduced the deviation between the two data sets. Nonetheless, the deviation between the two data sets caused by factors other than RSR differences did not permit a clearcut comparison of the techniques. Some recommendations regarding the techniques to select for a particular application are provided.Finally, this research introduces the concept of RSR difference index (RDI) to quantify the spectral differences between two spectral bands.

Plant species richness prediction from DESIS hyperspectral data: A comparison study on feature extraction procedures and regression models

The diversity of terrestrial vascular plants plays a key role in maintaining the stability and productivity of ecosystems. Monitoring species compositional diversity across large spatial scales is challenging and time consuming. Airborne hyperspectral imaging has shown promise for measuring plant diversity remotely, but to operationalise these efforts over large regions we need to advance satellite-based alternatives. The advanced spectral and spatial specification of the recently launched DESIS (the DLR Earth Sensing Imaging Spectrometer) instrument provides a unique opportunity to test the potential for monitoring plant species diversity with spaceborne hyperspectral data. This study provides a quantitative assessment on the ability of DESIS hyperspectral data for predicting plant species richness in two different habitat types in southeast Australia. Spectral features were first extracted from the DESIS spectra, then regressed against on-ground estimates of plant species richness, with a two-fold cross validation scheme to assess the predictive performance. We tested and compared the effectiveness of Principal Component Analysis (PCA), Canonical Correlation Analysis (CCA), and Partial Least Squares analysis (PLS) for feature extraction, and Kernel Ridge Regression (KRR), Gaussian Process Regression (GPR), and Random Forest Regression (RFR) for species richness prediction. The best prediction results were r=0.76 and RMSE=5.89 for the Southern Tablelands region, and r=0.68 and RMSE=5.95 for the Snowy Mountains region. Relative importance analysis for the DESIS spectral bands showed that the red-edge, red, and blue spectral regions were more important for predicting plant species richness than the green bands and the near-infrared bands beyond red-edge. We also found that the DESIS hyperspectral data performed better than Sentinel-2 multispectral data in the prediction of plant species richness. Our results provide a quantitative reference for future studies exploring the potential of spaceborne hyperspectral data for plant biodiversity mapping.

Adjacent Bi-Hierarchical Network for Scene Parsing of Remote Sensing Images

Driven by the rapid development and application of earth observation sensors, the scene parsing of remote sensing images (RSIs) has attracted extensive research attention in recent years. Restricted by the limited local receptive field of successive convolution layers, traditional models of scene parsing cannot effectively and interactively utilize the local-global information and digital surface model (DSM) of RSIs. Comparatively, accurate scene parsing faces more challenges because of unbalanced categories, small targets, and more complex scenes. To address these challenges, herein, we propose a novel adjacent bi-hierarchical network (ABHNet). Specifically, we introduce a DSM-enhanced (DSE) module to excavate characteristic DSM information from DSM images and enhance the red, green, and blue (RGB) features by exploiting informative cues between RGB and DSM modalities. In addition, an adjacent context exploration (ACE) module is proposed, which contains current and adjacent branches. The branches first exploit multiscale complementary characteristics of multilevel features and then integrate these features by applying adjacent exploration. Our model includes five ACE modules—three are deployed to activate detailed features and two obtain deep-guided features. The mutual collaboration of deep and detailed features is more beneficial to the segmentation of small objects. Extensive experiments on two remote sensing benchmark datasets (ISPRS Potsdam and Vaihingen) showed that the proposed ABHNet qualitatively and quantitatively outperformed other methods.