@article{MTMT:34651168, title = {Applied soft classes and fuzzy confusion in a patchwork semi-arid ecosystem: Stitching together classification techniques to preserve ecologically-meaningful information}, url = {https://m2.mtmt.hu/api/publication/34651168}, author = {Enterkine, Josh and Caughlin, T. Trevor and Dashti, Hamid and Glenn, Nancy F.}, doi = {10.1016/j.rse.2023.113853}, journal-iso = {REMOTE SENS ENVIRON}, journal = {REMOTE SENSING OF ENVIRONMENT}, volume = {300}, unique-id = {34651168}, issn = {0034-4257}, keywords = {invasive species; Clustering; Time series; Biological soil crust; drylands; Unmixing; semi-arid}, year = {2024}, eissn = {1879-0704} } @article{MTMT:34562370, title = {Grassland vertical height heterogeneity predicts flower and bee diversity: an UAV photogrammetric approach}, url = {https://m2.mtmt.hu/api/publication/34562370}, author = {Torresani, M. and Rocchini, D. and Ceola, G. and de, Vries J.P.R. and Feilhauer, H. and Moudrý, V. and Bartholomeus, H. and Perrone, M. and Anderle, M. and Gamper, H.A. and Chieffallo, L. and Guatelli, E. and Gatti, R.C. and Kleijn, D.}, doi = {10.1038/s41598-023-50308-9}, journal-iso = {SCI REP}, journal = {SCIENTIFIC REPORTS}, volume = {14}, unique-id = {34562370}, issn = {2045-2322}, year = {2024}, eissn = {2045-2322} } @article{MTMT:33954213, title = {Scientific maps should reach everyone: The cblindplot R package to let colour blind people visualise spatial patterns}, url = {https://m2.mtmt.hu/api/publication/33954213}, author = {Rocchini, Duccio and Nowosad, Jakub and D'Introno, Rossella and Chieffallo, Ludovico and Bacaro, Giovanni and Gatti, Roberto Cazzolla and Foody, Giles M. and Furrer, Reinhard and Gabor, Lukas and Malavasi, Marco and Marcantonio, Matteo and Marchetto, Elisa and Moudry, Vitezslav and Ricotta, Carlo and Simova, Petra and Torresani, Michele and Thouverai, Elisa}, doi = {10.1016/j.ecoinf.2023.102045}, journal-iso = {ECOL INFORM}, journal = {ECOLOGICAL INFORMATICS}, volume = {76}, unique-id = {33954213}, issn = {1574-9541}, abstract = {Maps represent powerful tools to show the spatial variation of a variable in a straightforward manner. A crucial aspect in map rendering for its interpretation by users is the gamut of colours used for displaying data. One part of this problem is linked to the proportion of the human population that is colour blind and, therefore, highly sensitive to colour palette selection. The aim of this paper is to present the cblindplot R package and its founding function -cblind.plot() -which enables colour blind people to just enter an image in a coding workflow, simply set their colour blind deficiency type, and immediately get as output a colour blind friendly plot. We will first describe in detail colour blind problems, and then show a step by step example of the function being proposed. While examples exist to provide colour blind people with proper colour palettes, in such cases (i) the workflow include a separate import of the image and the application of a set of colour ramp palettes and (ii) albeit being well documented, there are many steps to be done before plotting an image with a colour blind friendly ramp palette. The function described in this paper, on the contrary, allows to (i) automatically call the image inside the function without any initial import step and (ii) explicitly refer to the colour blind deficiency type being experienced, to further automatically apply the proper colour ramp palette.}, keywords = {Mapping; SCIENTIFIC COMMUNICATION; Ecological informatics; colour blindness; Computational ecology}, year = {2023}, eissn = {1878-0512} } @article{MTMT:33795872, title = {A novel approach for surveying flowers as a proxy for bee pollinators using drone images}, url = {https://m2.mtmt.hu/api/publication/33795872}, author = {Torresani, M. and Kleijn, D. and de, Vries J.P.R. and Bartholomeus, H. and Chieffallo, L. and Cazzolla, Gatti R. and Moudrý, V. and Da, Re D. and Tomelleri, E. and Rocchini, D.}, doi = {10.1016/j.ecolind.2023.110123}, journal-iso = {ECOL INDIC}, journal = {ECOLOGICAL INDICATORS}, volume = {149}, unique-id = {33795872}, issn = {1470-160X}, year = {2023}, eissn = {1872-7034} } @article{MTMT:33721066, title = {Can vegetation be discretely classified in species-poor environments? Testing plant community concepts for vegetation monitoring on sub-Antarctic Marion Island}, url = {https://m2.mtmt.hu/api/publication/33721066}, author = {van, der Merwe S. and Greve, M. and Skowno, A.L. and Hoffman, M.T. and Cramer, M.D.}, doi = {10.1002/ece3.9681}, journal-iso = {ECOL EVOL}, journal = {ECOLOGY AND EVOLUTION}, volume = {13}, unique-id = {33721066}, issn = {2045-7758}, year = {2023}, eissn = {2045-7758} } @article{MTMT:33954215, title = {Characterizing Uncertainty and Enhancing Utility in Remotely Sensed Land Cover Using Error Matrices Localized in Canonical Correspondence Analysis Ordination Space}, url = {https://m2.mtmt.hu/api/publication/33954215}, author = {Wan, Yue and Zhang, Jingxiong and Zhang, Wangle and Zhang, Ying and Yang, Wenjing and Wang, Jianxu and Chukwunonso, Okafor Somtoochukwu and Nadeeka, Asurapplullige Milani Tharuka}, doi = {10.3390/rs15051367}, journal-iso = {REMOTE SENS-BASEL}, journal = {REMOTE SENSING}, volume = {15}, unique-id = {33954215}, abstract = {In response to uncertainty in remotely sensed land cover products, there is continuing research on accuracy assessment and analysis. Given reference sample data, accuracy indicators are commonly estimated based on error matrices, from which areal extents of different cover types are also estimated. There are merits to explore the ways utilities of land cover products may be further enhanced beyond map face values and conventional area estimation. This paper presents an integrative method (CCAErrMat) for uncertainty characterization and utility enhancement. This works through reference-map cover type co-occurrence analyses based on error matrices localized in canonical correspondence analysis (CCA) ordination space rather than in geographic space to overcome the sparsity of reference sample data. The aforementioned co-occurrence analyses facilitate quantification of accuracy indicators, identification of correctly classified and perfectly misclassified pixels, and prediction of reference class probabilities, all at individual pixels. Moreover, these predicted reference class probabilities are used as auxiliary variables to formulate model-assisted area estimation, further enhancing map utilities. Extensions to CCAErrMat are also investigated as a way to bypass the pre-computing of map class occurrence pattern indices as candidate explanatory variables for CCAErrMat, leading to two variant methods: CCACCAErrMat and CNNCCAErrMat. A case study based in Wuhan municipality, central China was undertaken to compare the proposed method against alternative methods, including CCA-separate and CNN-separate. The advantages of CCAErrMat and CCACCAErrMat were confirmed. The proposed method is recommendable for characterizing uncertainty and enhancing utilities in land cover maps by analyzing locally constrained error matrices. The method is also cost-effective in terms of reference sample data, as requirements for them are similar to those for conventional accuracy assessments.}, keywords = {Convolutional neural network (CNN); local accuracy; canonical correspondence analysis (CCA); Area estimation; reference sample; model-assisted estimation; error matrices; ordination space; class occurrences}, year = {2023}, eissn = {2072-4292}, orcid-numbers = {Zhang, Wangle/0000-0002-9769-4277} } @article{MTMT:33954214, title = {RGB vs. Multispectral imagery: Mapping aapa mire plant communities with UAVs}, url = {https://m2.mtmt.hu/api/publication/33954214}, author = {Wolff, Franziska and Kolari, Tiina H. M. and Villoslada, Miguel and Tahvanainen, Teemu and Korpelainen, Pasi and Zamboni, Pedro A. P. and Kumpula, Timo}, doi = {10.1016/j.ecolind.2023.110140}, journal-iso = {ECOL INDIC}, journal = {ECOLOGICAL INDICATORS}, volume = {148}, unique-id = {33954214}, issn = {1470-160X}, abstract = {Plant communities of mires can be linked to important ecological processes, such as carbon storage and gas fluxes. As indicators of ecosystem dynamics, knowledge about their distribution and condition can support ecosystem assessment. Mapping mire vegetation enables monitoring at ecosystem-scale, which can be done with UAVs (Unmanned Aerial Vehicles). Depending on the mounted sensor and the spectral signals recorded, various attributes of plant communities can be retrieved. However, it is uncertain to what extent plant communities can be derived, as mapping vegetation on detailed level remains challenging due to overlapping spectral signatures of plant species. Advancing technology offers the choice between low cost RGB and multispectral sensors as well as a variety of classification methods to overcome these challenges. Therefore, we used K-means unsupervised classification and Random Forest supervised classification with different input variables to map microtopo-graphical patterns and plant communities of two aapa mires as resolved by hierarchical clustering. This extensive approach allowed the assessment of both classifier's strength and weaknesses, as well as the criteria of selecting suitable input data. UAV-RGB and multispectral imagery with associated spectral and topographical indices of both 0.05 m and 0.30 m spatial resolution were used for the K-means method. We assessed the relationship between these generated spectral classes and plant community clusters. The clusters further served as training and validation labels for to classify the high resolution, multispectral UAV-data (0.05 m) using Random Forest. Our study demonstrates that maps reflecting microtopograpical patterns and a wetness gradient can be produced with low-cost RGB imagery and unsupervised classification. Despite this linkage to plant communities, enhanced and detailed maps of plant community distribution can only be achieved with multispectral data and robust machine learning techniques. Random forest classifications showed good overall accuracies (0.59 - 0.82) in mapping microtopographical patterns and plant communities based on hierarchical clustering of vegetation data. While the strength of both classifiers lies in the distinction of bog hummock communities, classification per-formance was weaker between different transition and lawn community types. Casual misclassifications occurred also for communities along the transition of microtopographical patterns. The main obstacle for accurate mapping remains the overlap of spectral signatures from species and spectral noise originating from wetness in mires that lead to misclassification. Future studies addressing plant community and diversity mapping should therefore consider the origin of spectral variation with further sensors.}, keywords = {Spectral reflectance; Image classification; Hierarchical clustering; random forest; K -means}, year = {2023}, eissn = {1872-7034}, orcid-numbers = {Wolff, Franziska/0000-0002-6667-4169} } @article{MTMT:33471672, title = {Landsat-8 based coastal ecosystem mapping in South Africa using random forest classification in Google Earth Engine}, url = {https://m2.mtmt.hu/api/publication/33471672}, author = {Bessinger, Mariel and Luck-Vogel, Melanie and Skowno, Andrew and Conrad, Ferozah}, doi = {10.1016/j.sajb.2022.08.014}, journal-iso = {S AFR J BOT}, journal = {SOUTH AFRICAN JOURNAL OF BOTANY}, volume = {150}, unique-id = {33471672}, issn = {0254-6299}, abstract = {Coastlines worldwide are home to an increasing number of people and are subject to many pressures. This, combined with natural dynamics and hazards, often results in the degradation of coastal and marine ecosys-tems and infrastructure. Therefore, it is necessary to adopt effective management strategies to ensure sus-tainable use of coastal ecosystems, which requires up-to-date data on the extent of coastal ecosystems. This research aimed to create a coastal ecosystem land cover map for South Africa using the random forest algo-rithm to classify Landsat 8 imagery. Processing was done using the Google Earth Engine platform. A total of 522 Landsat 8 images were called to create a median image for classification. The impact of the number of trees, the number of variables per split, and variable selection on overall classification accuracy and Kappa values were evaluated. This was done by increasing the number of trees from 100 to 500 with increments of 100, setting the number of variables per split to three, four or five, and reducing the number of input varia-bles from the original 18 variables, to the 10 most important variables, to the 5 most important variables, based on variable importance scores. Results suggest that the number of input variables used in the model had a greater impact on accuracy than the number of trees used, or the number of variables used per split. The average overall accuracy was 82.28%, with values ranging between 75.33% and 86.70%, while the average Kappa was 0.8068 and values ranged between 0.7310 and 0.8550. The model with the highest overall accu-racy was the model using all input variables, 500 trees, and three variables per split. A major challenge was the misclassification of certain vegetation classes due to the complex successional mosaic they form, causing mixed signals and generally lower classification accuracy. Despite model limitations, results were satisfactory and have shown that coastal land cover classification and monitoring could be aided by the rapid classifica-tion of Landsat 8 imagery in Google Earth Engine using the random forest algorithm. (c) 2022 SAAB. Published by Elsevier B.V. All rights reserved.}, keywords = {remote sensing; conservation planning; spatial planning; random forest; Ecosystem-based classification; Coastal mapping}, year = {2022}, eissn = {1727-9321}, pages = {928-939}, orcid-numbers = {Skowno, Andrew/0000-0002-2726-7886; Conrad, Ferozah/0000-0003-4242-5261} } @article{MTMT:33489858, title = {Deforestation by Afforestation: Land Use Change in the Coastal Range of Chile}, url = {https://m2.mtmt.hu/api/publication/33489858}, author = {Braun, Andreas C.}, doi = {10.3390/rs14071686}, journal-iso = {REMOTE SENS-BASEL}, journal = {REMOTE SENSING}, volume = {14}, unique-id = {33489858}, abstract = {In southern Chile, an establishment of a plantation-based forest industry occurred early in the industrial era. Forest companies claim that plantations were established on eroded lands. However, the plantation industry is under suspicion to have expanded its activities by clearing near-natural forests since the early 1970s. This paper uses a methodologically complex classification approach from own previously published research to elucidate land use dynamics in southern Chile. It uses spatial data (extended morphological profiles) in addition to spectral data from historical Landsat imagery, which are fusioned by kernel composition and then classified in a multiple classifier system (based on support, import and relevance vector machines). In a large study area (similar to 67,000 km(2)), land use change is investigated in a narrow time frame (five-year steps from 1975 to 2010) in a twoway (prospective and retrospective) analysis. The results are discussed synoptically with other results on Chile. Two conclusions can be drawn for the coastal range. Near-natural forests have always been felled primarily in favor of the plantation industry. Vice versa, industrial plantations have always been primarily established on sites, that were formerly forest covered. This refutes the claim that Chilean plantations were established primarily to restore eroded lands; also known as badlands. The article further shows that Chile is not an isolated case of deforestation by afforestation, which has occurred in other countries alike. Based on the findings, it raises the question of the extent to which the Chilean example could be replicated in other countries through afforestation by market economy and climate change mitigation.}, keywords = {PATTERN RECOGNITION; Deforestation; land-use change; LANDSAT; spectral-spatial classification}, year = {2022}, eissn = {2072-4292} } @article{MTMT:33489856, title = {Spatially Stratified and Multi-Stage Approach for National Land Cover Mapping Based on Sentinel-2 Data and Expert Knowledge}, url = {https://m2.mtmt.hu/api/publication/33489856}, author = {Costa, Hugo and Benevides, Pedro and Moreira, Francisco D. and Moraes, Daniel and Caetano, Mario}, doi = {10.3390/rs14081865}, journal-iso = {REMOTE SENS-BASEL}, journal = {REMOTE SENSING}, volume = {14}, unique-id = {33489856}, abstract = {Portugal is building a land cover monitoring system to deliver land cover products annually for its mainland territory. This paper presents the methodology developed to produce a prototype relative to 2018 as the first land cover map of the future annual map series (COSsim). A total of thirteen land cover classes are represented, including the most important tree species in Portugal. The mapping approach developed includes two levels of spatial stratification based on landscape dynamics. Strata are analysed independently at the higher level, while nested sublevels can share data and procedures. Multiple stages of analysis are implemented in which subsequent stages improve the outputs of precedent stages. The goal is to adjust mapping to the local landscape and tackle specific problems or divide complex mapping tasks in several parts. Supervised classification of Sentinel-2 time series and post-classification analysis with expert knowledge were performed throughout four stages. The overall accuracy of the map is estimated at 81.3% (+/- 2.1) at the 95% confidence level. Higher thematic accuracy was achieved in southern Portugal, and expert knowledge significantly improved the quality of the map.}, keywords = {machine learning; random forest; satellite image; multi-temporal; land cover land use; COSsim}, year = {2022}, eissn = {2072-4292}, orcid-numbers = {Costa, Hugo/0000-0001-6207-8223; Moraes, Daniel/0000-0002-4568-8182; Caetano, Mario/0000-0001-8913-7342} } @article{MTMT:33489860, title = {About the link between biodiversity and spectral variation}, url = {https://m2.mtmt.hu/api/publication/33489860}, author = {Fassnacht, Fabian Ewald and Mullerova, Jana and Conti, Luisa and Malavasi, Marco and Schmidtlein, Sebastian}, doi = {10.1111/avsc.12643}, journal-iso = {APP VEGE SCI}, journal = {APPLIED VEGETATION SCIENCE}, volume = {25}, unique-id = {33489860}, issn = {1402-2001}, abstract = {Aim The spectral variability hypothesis (SVH) suggests a link between spectral variation and plant biodiversity. The underlying assumptions are that higher spectral variation in canopy reflectance (depending on scale) is caused by either (1) variation in habitats or linked vegetation types or plant communities with their specific optical community traits or (2) variation in the species themselves and their specific optical traits. Methods The SVH was examined in several empirical remote-sensing case studies, which often report some correlation between spectral variation and biodiversity-related variables (mostly plant species counts); however, the strength of the observed correlations varies between studies. In contrast, studies focussing on understanding the causal relationship between (plant) species counts and spectral variation remain scarce. Here, we discuss these causal relationships and support our perspectives through simulations and experimental data. Results We reveal that in many situations the spectral variation caused by species or functional traits is subtle in comparison to other factors such as seasonality and physiological status. Moreover, the degree of contrast in reflectance has little to do with the number but rather with the identity of the species or communities involved. Hence, spectral variability should not be expressed based on contrast but rather based on metrics expressing manifoldness. While we describe cases where a certain link between spectral variation and plant species diversity can be expected, we believe that as a scientific hypothesis (which suggests a general validity of this assumed relationship) the SVH is flawed and requires refinement. Conclusions To this end we call for more research examining the drivers of spectral variation in vegetation canopies and their link to plant species diversity and biodiversity in general. Such research will allow critically assessing under which conditions spectral variation is a useful indicator for biodiversity monitoring and how it could be integrated into monitoring networks.}, keywords = {Biodiversity; MONITORING; remote sensing; VEGETATION; spectral variability hypothesis}, year = {2022}, eissn = {1654-109X}, orcid-numbers = {Mullerova, Jana/0000-0001-7331-3479; Conti, Luisa/0000-0001-8047-1467; Malavasi, Marco/0000-0002-9639-1784; Schmidtlein, Sebastian/0000-0003-1888-1865} } @article{MTMT:33061334, title = {Sentinel-2 Enables Nationwide Monitoring of Single Area Payment Scheme and Greening Agricultural Subsidies in Hungary}, url = {https://m2.mtmt.hu/api/publication/33061334}, author = {Henits, László and Szerletics, Ákos and Szokol, Dávid and Szlovák, Gergely and Gojdár, Emese and Zlinszky, András}, doi = {10.3390/rs14163917}, journal-iso = {REMOTE SENS-BASEL}, journal = {REMOTE SENSING}, volume = {14}, unique-id = {33061334}, abstract = {The verification and monitoring of agricultural subsidy claims requires combined evaluation of several criteria at the scale of over a million cultivation units. Sentinel-2 satellite imagery is a promising data source and paying agencies are encouraged to test their pre-operational use. Here, we present the outcome of the Hungarian agricultural subsidy monitoring pilot: our goal was to propose a solution based on open-source components and evaluate the main strengths and weaknesses for Sentinel-2 in the framework of a complex set of tasks. These include the checking of the basic cultivation of grasslands and arable land and compliance to the criteria of ecological focus areas. The processing of the satellite data was conducted based on random forest for crop classification and the detection of cultivation events was conducted based on NDVI (Normalized Differential Vegetation Index) time series analysis results. The outputs of these processes were combined in a decision tree ruleset to provide the final results. We found that crop classification provided good performance (overall accuracy 88%) for 22 vegetation classes and cultivation detection was also reliable when compared to on-screen visual interpretation. The main limitation was the size of fields, which were frequently small compared to the spatial resolution of the images: more than 4% of the parcels had to be excluded, although these represent less than 3% of the cultivated area of Hungary. Based on these results, we find that operational satellite-based monitoring is feasible for Hungary, and expect further improvements from integration with Sentinel-1 due to additional temporal resolution.}, year = {2022}, eissn = {2072-4292}, orcid-numbers = {Zlinszky, András/0000-0002-9717-0043} } @article{MTMT:33489853, title = {Seabed morphology and bed shear stress predict temperate reef habitats in a high energy marine region}, url = {https://m2.mtmt.hu/api/publication/33489853}, author = {Jackson-Bue, Tim and Whitton, Timothy A. and Roberts, Michael J. and Brown, Alice Goward and Amir, Hana and King, Jonathan and Powell, Ben and Rowlands, Steven J. and Jones, Gerallt Llewelyn and Davies, Andrew J.}, doi = {10.1016/j.ecss.2022.107934}, journal-iso = {ESTUAR COAST SHELF S}, journal = {ESTUARINE COASTAL AND SHELF SCIENCE}, volume = {274}, unique-id = {33489853}, issn = {0272-7714}, abstract = {High energy marine regions host ecologically important habitats like temperate reefs, but are less anthropogenically developed and understudied compared to lower energy waters. In the marine environment direct habitat observation is limited to small spatial scales, and high energy waters present additional logistical challenges and constraints. Semi-automated predictive habitat mapping is a cost-effective tool to map benthic habitats across large extents, but performance is context specific. High resolution environmental data used for predictive mapping are often limited to bathymetry, acoustic backscatter and their derivatives. However, hydrodynamic energy at the seabed is a critical habitat structuring factor and likely an important, yet rarely incorporated, predictor of habitat composition and spatial patterning. Here, we used a machine learning classification approach to map temperate reef substrate and biogenic reef habitat in a tidal energy development area, incorporating bathymetric derivatives at multiple scales and simulated tidally induced seabed shear stress. We mapped reef substrate (four classes: sediment (not reef), stony reef (low resemblance), stony reef (medium - high resemblance) and bedrock reef) with overall balanced accuracy of 71.7%. Our model to predict potential biogenic Sabellaria spinulosa reef performed less well with an overall balanced accuracy of 63.4%. Despite low performance metrics for the target class of potential reef in this model, it still provided insight into the importance of different environmental variables for mapping S. spinulosa biogenic reef habitat. Tidally induced mean bed shear stress was one of the most important predictor variables for both reef substrate and biogenic reef models, with ruggedness calculated at multiple scales from 3 m to 140 m also important for the reef substrate model. We identified previously unresolved relationships between temperate reef spatial distribution, hydrodynamic energy and seabed three-dimensional structure in energetic waters. Our findings contribute to a better understanding of the spatial ecology of high energy marine ecosystems and will inform evidence-based decision making for sustainable development, particularly within the growing tidal energy sector.}, keywords = {machine learning; hydrodynamics; bathymetry; ecosystem management; spatial scale; Tidal energy; Benthic ecology; Seascape ecology; Reef mapping; Sabellaria spinulosa}, year = {2022}, eissn = {1096-0015}, orcid-numbers = {Amir, Hana/0000-0001-9625-6294; King, Jonathan/0000-0002-4106-9368; Powell, Ben/0000-0003-4358-7289} } @inproceedings{MTMT:33489849, title = {PROBABILISTIC VEGETATION TRANSITIONS IN DUNES BY COMBINING SPECTRAL AND LIDAR DATA}, url = {https://m2.mtmt.hu/api/publication/33489849}, author = {Kathmann, H. S. and van Natijne, A. L. and Lindenbergh, R. C.}, booktitle = {2022 24th ISPRS Congress on Imaging Today, Foreseeing Tomorrow, Commission II}, doi = {10.5194/isprs-archives-XLIII-B2-2022-1033-2022}, unique-id = {33489849}, abstract = {Monitoring the status of the vegetation is required for nature conservation. This monitoring task is time consuming as kilometers of area have to be investigated and classified. To make this task more manageable, remote sensing is used. The acquisition of airplane remote sensing data is dependent on weather conditions and permission to fly in the busy airspace above the Netherlands. These conditions make it difficult to get a new, dedicated acquisition every year. Therefore, alternatives for this dependency on dedicated airplane surveys are needed. One alternative is the use of optical satellite imagery, as this type of data has improved rapidly in the last decade both in terms of resolution and revisit time. For this study, 0.5 m resolution satellite imagery from the Superview satellite is combined with geometric height data from the Dutch national airborne LiDAR elevation data set AHN. Goal is to classify vegetation into three different classes: sand, grass and trees, apply this classification to multiple epochs, and analyze class transition patterns. Three different classification methods were compared: nearest centroid, random forest and neural network. We show that outcomes of all three methods can be interpreted as class probabilities, but also that these probabilities have different properties for each method. The classification is implemented for 11 different epochs on the Meijendel en Berkheide dunal area on the Dutch coast. We show that mixed probabilities (i.e. between two classes) agree well with class transition processes, and conclude that a shallow neural network combined with pure training samples applied on four different bands (RGB + relative DSM height) produces satisfactory results for the analysis of vegetation transitions with accuracies close to 100%.}, year = {2022}, pages = {1033-1040} } @article{MTMT:33107747, title = {Challenging the link between functional and spectral diversity with radiative transfer modeling and data}, url = {https://m2.mtmt.hu/api/publication/33107747}, author = {Pacheco-Labrador, J. and Migliavacca, M. and Ma, X. and Mahecha, M. and Carvalhais, N. and Weber, U. and Benavides, R. and Bouriaud, O. and Barnoaiea, I. and Coomes, D.A. and Bohn, F.J. and Kraemer, G. and Heiden, U. and Huth, A. and Wirth, C.}, doi = {10.1016/j.rse.2022.113170}, journal-iso = {REMOTE SENS ENVIRON}, journal = {REMOTE SENSING OF ENVIRONMENT}, volume = {280}, unique-id = {33107747}, issn = {0034-4257}, year = {2022}, eissn = {1879-0704} } @article{MTMT:33489847, title = {Correlation Analysis of Evapotranspiration, Emissivity Contrast and Water Deficit Indices: A Case Study in Four Eddy Covariance Sites in Italy with Different Environmental Habitats}, url = {https://m2.mtmt.hu/api/publication/33489847}, author = {Torresani, Michele and Masiello, Guido and Vendrame, Nadia and Gerosa, Giacomo and Falocchi, Marco and Tomelleri, Enrico and Serio, Carmine and Rocchini, Duccio and Zardi, Dino}, doi = {10.3390/land11111903}, journal-iso = {LAND-BASEL}, journal = {LAND (BASEL)}, volume = {11}, unique-id = {33489847}, abstract = {Evapotranspiration (ET) represents one of the essential processes controlling the exchange of energy by terrestrial vegetation, providing a strong connection between energy and water fluxes. Different methodologies have been developed in order to measure it at different spatial scales, ranging from individual plants to an entire watershed. In the last few years, several methods and approaches based on remotely sensed data have been developed over different ecosystems for the estimation of ET. In the present work, we outline the correlation between ET measured at four eddy covariance (EC) sites in Italy (situated either in forest or in grassland ecosystems) and (1) the emissivity contrast index (ECI) based on emissivity data from thermal infrared spectral channels of the MODIS and ASTER satellite sensors (CAMEL data-set); (2) the water deficit index (WDI), defined as the difference between the surface and dew point temperature modeled by the ECMWF (European Centre for Medium-Range Weather Forecasts) data. The analysis covers a time-series of 1 to 7 years depending on the site. The results showed that both the ECI and WDI correlate to the ET calculated through EC. In the relationship WDI-ET, the coefficient of determination ranges, depending on the study area, between 0.5 and 0.9, whereas it ranges between 0.5 and 0.7 when ET was correlated to the ECI. The slope and the sign of the latter relationship is influenced by the vegetation habitat, the snow cover (particularly in winter months) and the environmental heterogeneity of the area (calculated in this study through the concept of the spectral variation hypothesis using Rao's Q heterogeneity index).}, keywords = {HETEROGENEITY; Evapotranspiration; thermal infrared; emissivity; spectral variation hypothesis; Rao's Q index}, year = {2022}, eissn = {2073-445X}, orcid-numbers = {Torresani, Michele/0000-0001-7270-3619; Masiello, Guido/0000-0002-7986-8296; Vendrame, Nadia/0000-0002-2772-6755; Gerosa, Giacomo/0000-0002-5352-3222; Falocchi, Marco/0000-0003-4644-518X; Tomelleri, Enrico/0000-0001-6546-6459; Serio, Carmine/0000-0002-5931-7681; Zardi, Dino/0000-0002-3573-3920} } @article{MTMT:33489855, title = {Fuzzy model-based reconstruction of paleovegetation in Ethiopia}, url = {https://m2.mtmt.hu/api/publication/33489855}, author = {von Reumont, Frederik and Schabitz, Frank and Asrat, Asfawossen}, doi = {10.1080/17445647.2022.2082332}, journal-iso = {J MAPS}, journal = {JOURNAL OF MAPS}, unique-id = {33489855}, issn = {1744-5647}, abstract = {We introduce a new method to compute plant distribution in Ethiopia under paleoclimatic conditions using fuzzy logic. Using a published map of the potential vegetation for Ethiopia we decipher the boundary conditions for the main vegetation units shown, reflecting modern climatic conditions for temperature and precipitation in this region. Fuzzy logic using these climatic values on a GIS platform then derived the computational map of the potential vegetation. Comparing it with the original map shows a general correspondence of about 90%. By changing the underlying climate parameters, we then used this model for hypothetical paleoclimatic conditions to simulate the vegetational response on these changed climate settings. Finally, vegetational response maps for Ethiopia are presented for two scenarios: (i) a colder and drier condition (such as the Last Glacial Maximum) and (ii) a warmer and wetter condition (such as the last interglacial) than today.}, keywords = {fuzzy logic; paleoclimate; paleovegetation; VEGETATION MODEL; potential vegetation maps}, year = {2022}, eissn = {1744-5647}, orcid-numbers = {von Reumont, Frederik/0000-0001-7592-3596; Asrat, Asfawossen/0000-0002-6312-8082} } @article{MTMT:33489845, title = {Integrating plot-based and remotely sensed data to map vegetation types in a New Zealand warm-temperate rainforest}, url = {https://m2.mtmt.hu/api/publication/33489845}, author = {Wiser, Susan. K. K. and McCarthy, James. K. K. and Bellingham, Peter. J. J. and Jolly, Ben and Meiforth, Jane. J. J. and Kaitiaki, Warawara Komiti}, doi = {10.1111/avsc.12695}, journal-iso = {APP VEGE SCI}, journal = {APPLIED VEGETATION SCIENCE}, volume = {25}, unique-id = {33489845}, issn = {1402-2001}, abstract = {Questions(1) What can be learned by extending a national classification into unsampled forest types? (2) Are both remotely sensed and environmental predictors needed to model and map associations? (3) For mapping, are LiDAR-generated canopy structure parameters or reflectance from spectral imagery more useful? (4) How can we assess uncertainty of a final map? LocationWarawara Forest, Northland, New Zealand. MethodsWe sampled 205 vegetation plots and assigned them to an existing national classification using the fuzzy classification framework of noise clustering. Plots too distinct to be assigned were used to define new associations. We produced spatial models of each association using boosted regression trees. Predictors included 11 environmental, 11 canopy reflectance, and 17 canopy structure variables. We created a composite map by assigning each map pixel to the association with the highest occurrence probability. We evaluated uncertainty by examining locations where no class was predicted with probability above 0.2 and by creating a confusion map based on entropy. ResultsForty-five plots were assigned to six of 79 existing national associations and 147 plots were used to define two new forest associations. Three shrubland types are widespread nationally, whereas two young forest types are northern. Three mature forest types are narrowly distributed nationally, with the new "High-elevation hardwood forest" largely restricted to Warawara Forest. Three associations were mapped using remotely sensed predictors alone, whereas two also required environmental predictors. Overall, canopy reflectance predictors explained more deviance than canopy structure. Examining locations where no association was predicted well and where multiple associations were predicted equally showed areas mapped as younger forests to have greatest uncertainty. ConclusionsIn answering our questions, we present a vegetation classification and map for Warawara Forest that provides a framework to guide the indigenous people's management responses to threats to valued communities and their species.}, keywords = {UNCERTAINTY; remote sensing; LIDAR; Vegetation map; Vegetation classification; Sentinel-2; noise clustering; boosted regression trees; community distribution modelling; warm temperate rainforest}, year = {2022}, eissn = {1654-109X} } @article{MTMT:32329740, title = {Are urban material gradients transferable between areas?}, url = {https://m2.mtmt.hu/api/publication/32329740}, author = {Ji, Chaonan and Heiden, Uta and Lakes, Tobia and Feilhauer, Hannes}, doi = {10.1016/j.jag.2021.102332}, journal-iso = {INT J APPL EARTH OBS}, journal = {INTERNATIONAL JOURNAL OF APPLIED EARTH OBSERVATION AND GEOINFORMATION}, volume = {100}, unique-id = {32329740}, issn = {1569-8432}, abstract = {Urban areas contain a complex mixture of surface materials resulting in mixed pixels that are challenging to handle with conventional mapping approaches. In particular, for spaceborne hyperspectral images (HSIs) with sufficient spectral resolution to differentiate urban surface materials, the spatial resolution of 30 m (e.g. EnMAP HSIs) makes it difficult to find the spectrally pure pixels required for detailed mapping of urban surface materials. Gradient analysis, which is commonly used in ecology to map natural vegetation consisting of a complex mixture of species, is therefore a promising and practical tool for pattern recognition of urban surface material mixtures. However, the gradients are determined in a data-driven manner, so analysis of their spatial transferability is urgently required. We selected two areas?the Ostbahnhof (Ost) area and the Nymphenburg (Nym) area in Munich, Germany?with simulated EnMAP HSIs and material maps, treating the Ost area as the target area and the Nym area as the well-known area. Three gradient analysis approaches were subsequently proposed for pattern recognition in the Ost area for the cases of (i) sufficient samples collected in the Ost area; (ii) some samples in the Ost area; and (iii) no samples in the Ost area. The Ost samples were used to generate an ordination space in case (i), while the Nym samples were used to create the ordination space to support the pattern recognition of the Ost area in cases (ii) and (iii). The Mantel statistical results show that the sample distributions in the two ordination spaces are similar, with high confidence (the Mantel statistics are 0.995 and 0.990, with a significance of 0.001 in 999 free permutations of the Ost and Nym samples). The results of the partial least square regression models and 10-fold cross-validation show a strong relationship (the calculation-validation R2 values on the first gradient among the three approaches are 0.898, 0.892; 0.760, 0.743; and 0.860, 0.836, and those on the second gradient are 0.433, 0.351; 0.698, 0.648; and 0.736, 0.646) between the ordination scores of the samples and their reflectance values. The mapping results of the Ost area from three approaches also show similar patterns (e.g. the distribution of vegetation, artificial materials, water, and ceremony area) and characteristics of urban structures (the intensity of buildings). Therefore, our findings can help assess the transferability of urban material gradients between similar urban areas.}, keywords = {Gradient analysis; IMAGING SPECTROSCOPY; transferability; Hyperspectral image; urban mapping}, year = {2021}, eissn = {1872-826X} }