Akpona Okujeni

The EnMAP-Box—A Toolbox and Application Programming Interface for EnMAP Data Processing

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 access to recent approaches for imaging spectroscopy data processing. The software is freely available and offers a range of tools and applications for the processing of spectral imagery, including classical processing tools for imaging spectroscopy data as well as powerful machine learning approaches or interfaces for the integration of methods available in scripting languages. A special developer version includes the full open source code, an application programming interface and an application wizard for easy integration and documentation of new developments. This paper gives an overview of the EnMAP-Box for users and developers, explains typical workflows along an application example and exemplifies the concept for making it a frequently used and constantly extended platform for imaging spectroscopy applications.

A Comparison of Advanced Regression Algorithms for Quantifying Urban Land Cover

Quantitative methods for mapping sub-pixel land cover fractions are gaining increasing attention, particularly with regard to upcoming hyperspectral satellite missions. We evaluated five advanced regression algorithms combined with synthetically mixed training data for quantifying urban land cover from HyMap data at 3.6 and 9 m spatial resolution. Methods included support vector regression (SVR), kernel ridge regression (KRR), artificial neural networks (NN), random forest regression (RFR) and partial least squares regression (PLSR). Our experiments demonstrate that both kernel methods SVR and KRR yield high accuracies for mapping complex urban surface types, i.e., rooftops, pavements, grass- and tree-covered areas. SVR and KRR models proved to be stable with regard to the spatial and spectral differences between both images and effectively utilized the higher complexity of the synthetic training mixtures for improving estimates for coarser resolution data. Observed deficiencies mainly relate to known problems arising from spectral similarities or shadowing. The remaining regressors either revealed erratic (NN) or limited (RFR and PLSR) performances when comprehensively mapping urban land cover. Our findings suggest that the combination of kernel-based regression methods, such as SVR and KRR, with synthetically mixed training data is well suited for quantifying urban land cover from imaging spectrometer data at multiple scales.

Using Class Probabilities to Map Gradual Transitions in Shrub Vegetation from Simulated EnMAP Data

Monitoring natural ecosystems and ecosystem transitions is crucial for a better understanding of land change processes. By providing synoptic views in space and time, remote sensing data have proven to be valuable sources for such purposes. With the forthcoming Environmental Mapping and Analysis Program (EnMAP), frequent and area-wide mapping of natural environments by means of high quality hyperspectral data becomes possible. However, the amplified spectral mixing due to the sensor’s ground sampling distance of 30 m on the one hand and the patterns of natural landscapes in the form of gradual transitions between different land cover types on the other require special attention. Based on simulated EnMAP data, this study focuses on mapping shrub vegetation along a landscape gradient of shrub encroachment in a semi-arid, natural environment in Portugal. We demonstrate how probability outputs from a support vector classification (SVC) model can be used to extend a hard classification by information on shrub cover fractions. This results in a more realistic representation of gradual transitions in shrub vegetation maps. We suggest a new, adapted approach for SVC parameter selection: During the grid search, parameter pairs are evaluated with regard to the prediction of synthetically mixed test data, representing shrub to non-shrub transitions, instead of the hard classification of original, discrete test data. Validation with an unbiased, equalized random sampling shows that the resulting shrub-class probabilities from adapted SVC more accurately represent shrub cover fractions (mean absolute error/root mean squared error of 16.3%/23.2%) compared to standard SVC (17.1%/29.5%). Simultaneously, the discrete classification output was considerably improved by incorporating synthetic mixtures into parameter selection (averaged F1 accuracies increased from 72.4% to 81.3%). Based on our findings, the integration of synthetic mixtures into SVC parameterization allows the use of SVC for sub-pixel cover fraction estimation and, this way, can be recommended for deriving improved qualitative and quantitative descriptions of gradual transitions in shrub vegetation. The approach is therefore of high relevance for mapping natural ecosystems from future EnMAP data.

Monitoring Natural Ecosystem and Ecological Gradients: Perspectives with EnMAP

In times of global environmental change, the sustainability of human–environment systems is only possible through a better understanding of ecosystem processes. An assessment of anthropogenic environmental impacts depends upon monitoring natural ecosystems. These systems are intrinsically complex and dynamic, and are characterized by ecological gradients. Remote sensing data repeatedly collected in a systematic manner are suitable for describing such gradual changes over time and landscape gradients, e.g., through information on the vegetation’s phenology. Specifically, imaging spectroscopy is capable of describing ecosystem processes, such as primary productivity or leaf water content of vegetation. Future spaceborne imaging spectroscopy missions like the Environmental Mapping and Analysis Program (EnMAP) will repeatedly acquire high-quality data of the Earth’s surface, and will thus be extremely useful for describing natural ecosystems and the services they provide. In this conceptual paper, we present some of the preparatory research of the EnMAP Scientific Advisory Group (EnSAG) on natural ecosystems and ecosystem transitions. Through two case studies we illustrate the usage of spectral indices derived from multi-date imaging spectroscopy data at EnMAP scale, for mapping vegetation gradients. We thus demonstrate the benefit of future EnMAP data for monitoring ecological gradients and natural ecosystems.

Sensing of Photosynthetic Activity of Crops

The light use efficiency of photosynthesis dynamically adapts to environmental factors and is one major factor determining crop yield. Optical remote sensing techniques have the potential to detect physiological and biochemical changes in plant ecosystems, and non-invasive detection of changes in photosynthetic energy conversion may be of great potential for managing agricultural production in a future bio-based economy. Here we give an overview on the principles of optical remote sensing in crop systems with a special emphasis on investigating hyperspectral reflectance data and the sun-induced fluorescence signal. Especially sun-induced fluorescence as a parameter, which becomes important in remote sensing research may have great potential quantifying the physiological status of the photosynthetic apparatus. Both remote sensing principles were applied during the CEFLES2 campaign in Southern France, where the structural and functional status of several crops was measured on the ground and using state-of-the-art optical remote sensing techniques. Sun-induced fluorescence measurements over a variety of crops showed that additional information can be retrieved also over dense canopies, where classical remote sensing signals often saturate. With a view to the future, we discuss how hyperspectral reflectance and sun-induced fluorescence can quantitatively be related to photosynthetic efficiency and help to measure and manage productivity of natural and agricultural ecosystems.

Import Vector Machines for Quantitative Analysis of Hyperspectral Data

In this letter we explore probabilities derived from an import vector machines (IVM) classifier as quantitative measures of class proportion. We have developed a parameter selection strategy that improves the description of class proportions. This strategy incorporates the use of spectral mixtures, which represent gradual class transitions, into the parameter selection process. In addition, we evaluated the sensitivity of our approach in regard to increasing training uncertainty and signal-to-noise ratio. The approach was tested for binary, two-class problems on hyperspectral in situ measurements. The IVM models generated with our parameter selection strategy achieved similar or even improved classification accuracies compared to parameter selection with the standard IVM classification approach. Furthermore, the respective class probabilities correlated highly with reference class proportions. This new strategy is less affected by the inclusion of random noise and relatively stable against increased training errors.

Ensemble Learning From Synthetically Mixed Training Data for Quantifying Urban Land Cover With Support Vector Regression

Generating synthetically mixed data from library spectra provides a direct means to train empirical regression models for subpixel mapping. In order to best represent the subpixel composition of image data, the generation of synthetic mixtures must incorporate a multitude of mixing possibilities. This can lead to an excessive amount of training samples. We show that increasing mixing complexity in the training set improves model performance when quantifying urban land cover with support vector regression (SVR). To cope with the challenging increase in the number of training samples, we propose the use of ensemble learning based on bootstrap aggregation from synthetically mixed training data. The workflow is tested on simulated spaceborne imaging spectrometer data acquired over Berlin, Germany. Comparisons to SVR without bagging and multiple endmember spectral mixture analysis reveal the usefulness of the methodology for quantitative urban mapping.

A Novel Spectral Library Pruning Technique for Spectral Unmixing of Urban Land Cover

Spectral unmixing of urban land cover relies on representative endmember libraries. For repeated mapping of multiple cities, the use of a generic spectral library, capturing the vast spectral variability of urban areas, would constitute a more operational alternative to the tedious development of image-specific libraries prior to mapping. The size and heterogeneity of such a generic library requires an efficient pruning technique to extract site-specific spectral libraries. We propose the “Automated MUsic and spectral Separability based Endmember Selection technique” (AMUSES), which selects endmember subsets with respect to the image to be processed, while accounting for internal redundancy. Experiments on simulated hyperspectral data from Brussels (Belgium) showed that AMUSES selects more relevant endmembers compared to the conventional Iterative Endmember Selection (IES) approach. This ultimately improved mapping results (kappa increased from 0.71 to 0.83). Experiments on real HyMap data from Berlin (Germany) using a combination of libraries from different cities underlined the potential of AMUSES for handling libraries with increasing levels of generality (RMSE decreased from 0.18 to 0.15, while only using 55% of the number of spectra compared to IES). Our findings contribute to the value of generic spectral databases in the development of efficient urban mapping workflows.

Subpixel Mapping of Urban Areas Using EnMAP Data and Multioutput Support Vector Regression

Hyperspectral remote sensing data offer the opportunity to map urban characteristics in detail. Though, adequate algorithms need to cope with increasing data dimensionality, high redundancy between individual bands, and often spectrally complex urban landscapes. The study focuses on subpixel quantification of urban land cover compositions using simulated environmental mapping and analysis program (EnMAP) data acquired over the city of Berlin, utilizing both machine learning regression and classification algorithms, i.e., multioutput support vector regression (MSVR), standard support vector regression (SVR), import vector machine classifier (IVM), and support vector classifier (SVC). The experimental setup incorporates a spectral library and a reference land cover fraction map used for validation purposes. The library spectra were synthetically mixed to derive quantitative training data for the classes vegetation, impervious surface, soil, and water. MSVR and SVR models were trained directly using the synthetic mixtures. For IVM and SVC, a modified hyperparameter selection approach is conducted to improve the description of urban land cover fractions by means of probability outputs. Validation results demonstrate the high potential of the MSVR for subpixel mapping in the urban context. MSVR outperforms SVR in terms of both accuracy and computational time. IVM and SVC work similarly well, yet with lower accuracies of subpixel fraction estimates compared to both regression approaches.

Optimizing mixed spectra generation for regression-based unmixing of land cover in urban areas

Regression-based unmixing for quantifying urban land cover at the subpixel scale requires mixed training spectra for model calibration. In this paper optimization and synthetic mixing of hyperspectral image endmember libraries for the calibration of unmixing models are investigated. APEX and HyMap airborne hyperspectral transects respectively covering Brussels and Berlin are used to produce an endmember library for unmixing, as well as reference land cover fractions for validation. The library is spectrally resampled, optimized and synthetically mixed to produce quantitative training data for unmixing of a Sentinel-2 surface reflectance image of Brussels (Belgium). Support Vector Regression models are developed for vegetation-impervious-soil land cover mapping. Findings may contribute to the use of multi-sensor data and to the demonstration of Sentinel-2s added value for quantitative urban land cover assessment.