RESUMO
Accurate plant-type (PT) detection forms an important basis for sustainable land management maintaining biodiversity and ecosystem services. In this sense, Sentinel-2 satellite images of the Copernicus program offer spatial, spectral, temporal, and radiometric characteristics with great potential for mapping and monitoring PTs. In addition, the selection of a best-performing algorithm needs to be considered for obtaining PT classification as accurate as possible. To date, no freely downloadable toolbox exists that brings the diversity of the latest supervised machine-learning classification algorithms (MLCAs) together into a single intuitive user-friendly graphical user interface (GUI). To fill this gap and to facilitate and automate the usage of MLCAs, here we present a novel GUI software package that allows systematically training, validating, and applying pixel-based MLCA models to remote sensing imagery. The so-called MLCA toolbox has been integrated within ARTMO's software framework developed in Matlab which implements most of the state-of-the-art methods in the machine learning community. To demonstrate its utility, we chose a heterogeneous case study scene, a landscape in Southwest Iran to map PTs. In this area, four main PTs were identified, consisting of shrub land, grass land, semi-shrub land, and shrub land-grass land vegetation. Having developed 21 MLCAs using the same training and validation, datasets led to varying accuracy results. Gaussian process classifier (GPC) was validated as the top-performing classifier, with an overall accuracy (OA) of 90%. GPC follows a Laplace approximation to the Gaussian likelihood under the supervised classification framework, emerging as a very competitive alternative to common MLCAs. Random forests resulted in the second-best performance with an OA of 86%. Two other types of ensemble-learning algorithms, i.e., tree-ensemble learning (bagging) and decision tree (with error-correcting output codes), yielded an OA of 83% and 82%, respectively. Following, thirteen classifiers reported OA between 70% and 80%, and the remaining four classifiers reported an OA below 70%. We conclude that GPC substantially outperformed all classifiers, and thus, provides enormous potential for the classification of a diversity of land-cover types. In addition, its probabilistic formulation provides valuable band ranking information, as well as associated predictive variance at a pixel level. Nevertheless, as these are supervised (data-driven) classifiers, performances depend on the entered training data, meaning that an assessment of all MLCAs is crucial for any application. Our analysis demonstrated the efficacy of ARTMO's MLCA toolbox for an automated evaluation of the classifiers and subsequent thematic mapping.
RESUMO
In the next few years, the new Copernicus Hyperspectral Imaging Mission (CHIME) is foreseen to be launched by the European Space Agency (ESA). This missions will provide an unprecedented amount of hyperspectral data, enabling new research possibilities within several fields of natural resources, including the "agriculture and food security" domain. In order to efficiently exploit this upcoming hyperspectral data stream, new processing methods and techniques need to be studied and implemented. In this work, the hybrid approach (HYB) and its variant, featuring sampling dimensionality reduction through active learning heuristics (HAL), were applied to CHIME-like data to evaluate the retrieval of crop traits, such as chlorophyll and nitrogen content at both leaf (LCC and LNC) and canopy level (CCC and CNC). The results showed that HYB was able to provide reliable estimations at canopy level (R2 = 0.79, RMSE = 0.38 g m-2 for CCC and R2 = 0.84, RMSE = 1.10 g m-2 for CNC) but failed at leaf level. The HAL approach improved retrieval accuracy at canopy level (best metric: R2 = 0.88 and RMSE = 0.21 g m-2 for CCC; R2 = 0.93 and RMSE = 0.71 g m-2 for CNC), providing good results also at leaf level (best metrics: R2 = 0.72 and RMSE = 3.31 µg cm-2 for LCC; R2 = 0.56 and RMSE = 0.02 mg cm-2 for LNC). The promising results obtained through the hybrid approach support the feasibility of an operational retrieval of chlorophyll and nitrogen content, e.g., in the framework of the future CHIME mission. However, further efforts are required to investigate the approach across different years, sites and crop types in order to improve its transferability to other contexts.
RESUMO
The current exponential increase of spatiotemporally explicit data streams from satellitebased Earth observation missions offers promising opportunities for global vegetation monitoring. Intelligent sampling through active learning (AL) heuristics provides a pathway for fast inference of essential vegetation variables by means of hybrid retrieval approaches, i.e., machine learning regression algorithms trained by radiative transfer model (RTM) simulations. In this study we summarize AL theory and perform a brief systematic literature survey about AL heuristics used in the context of Earth observation regression problems over terrestrial targets. Across all relevant studies it appeared that: (i) retrieval accuracy of AL-optimized training data sets outperformed models trained over large randomly sampled data sets, and (ii) Euclidean distance-based (EBD) diversity method tends to be the most efficient AL technique in terms of accuracy and computational demand. Additionally, a case study is presented based on experimental data employing both uncertainty and diversity AL criteria. Hereby, a a simulated training data base by the PROSAIL-PRO canopy RTM is used to demonstrate the benefit of AL techniques for the estimation of total leaf carotenoid content (Cxc ) and leaf water content (Cw ). Gaussian process regression (GPR) was incorporated to minimize and optimize the training data set with AL. Training the GPR algorithm on optimally AL-based sampled data sets led to improved variable retrievals compared to training on full data pools, which is further demonstrated on a mapping example. From these findings we can recommend the use of AL-based sub-sampling procedures to select the most informative samples out of large training data pools. This will not only optimize regression accuracy due to exclusion of redundant information, but also speed up processing time and reduce final model size of kernel-based machine learning regression algorithms, such as GPR. With this study we want to encourage further testing and implementation of AL sampling methods for hybrid retrieval workflows. AL can contribute to the solution of regression problems within the framework of operational vegetation monitoring using satellite imaging spectroscopy data, and may strongly facilitate data processing for cloud-computing platforms.
