The form of a remote sensing index is generally empirically defined, whether by choosing specific reflectance bands, equation forms or its coefficients. These spectral indices are used as preprocessing stage before object detection/classification. But no study seems to search for the best form through function approximation in order to optimize the classification and/or segmentation. The objective of this study is to develop a method to find the optimal index, using a statistical approach by gradient descent on different forms of generic equations. From six wavebands images, five equations have been tested, namely: linear, linear ratio, polynomial, universal function approximator and dense morphological. Few techniques in signal processing and image analysis are also deployed within a deep-learning framework. Performances of standard indices and DeepIndices were evaluated using two metrics, the dice (similar to f1-score) and the mean intersection over union (mIoU) scores. The study focuses on a specific multispectral camera used in near-field acquisition of soil and vegetation surfaces. These DeepIndices are built and compared to 89 common vegetation indices using the same vegetation dataset and metrics. As an illustration the most used index for vegetation, NDVI (Normalized Difference Vegetation Indices) offers a mIoU score of 63.98% whereas our best models gives an analytic solution to reconstruct an index with a mIoU of 82.19%. This difference is significant enough to improve the segmentation and robustness of the index from various external factors, as well as the shape of detected elements.
", "keywords": ["multi-spectral", "[INFO.INFO-TS] Computer Science [cs]/Signal and Image Processing", "multispectral", "Science", "0211 other engineering and technologies", "[SDV.SA.STA] Life Sciences [q-bio]/Agricultural sciences/Sciences and technics of agriculture", "02 engineering and technology", "Spectral indice", "Deep-learning", "image; precision agriculture; spectral indices; multi-spectral; deep-learning; vegetation segmentation", "deep-learning", "[INFO.INFO-TS]Computer Science [cs]/Signal and Image Processing", "[SDV.SA.STA]Life Sciences [q-bio]/Agricultural sciences/Sciences and technics of agriculture", "[SDV.BV]Life Sciences [q-bio]/Vegetal Biology", "[SDV.BV] Life Sciences [q-bio]/Vegetal Biology", "image", "precision agriculture", "Precision agriculture", "Vegetation segmentation", "Multi-spectral", "Q", "04 agricultural and veterinary sciences", "15. Life on land", "004", "Image", "vegetation segmentation", "spectral indices", "0401 agriculture", " forestry", " and fisheries"]}, "links": [{"href": "http://www.mdpi.com/2072-4292/13/12/2261/pdf"}, {"href": "https://www.mdpi.com/2072-4292/13/12/2261/pdf"}, {"href": "https://doi.org/10.3390/rs13122261"}, {"rel": "related", "href": "https://repository.soilwise-he.eu/cat/collections/metadata:main/items/Remote%20Sensing", "name": "related record", "description": "related record", "type": "application/json"}, {"rel": "self", "type": "application/geo+json", "title": "10.3390/rs13122261", "name": "item", "description": "10.3390/rs13122261", "href": "https://repository.soilwise-he.eu/cat/collections/metadata:main/items/10.3390/rs13122261"}, {"rel": "collection", "type": "application/json", "title": "Collection", "name": "collection", "description": "Collection", "href": "https://repository.soilwise-he.eu/cat/collections/metadata:main"}], "time": {"date": "2021-06-09T00:00:00Z"}}, {"id": "10.2139/ssrn.5042274", "type": "Feature", "geometry": null, "properties": {"license": "Open Access", "updated": "2026-09-21T16:19:02Z", "type": "Report", "created": "2024-12-09", "title": "Impact of Different Supervised Bare Soil Pixels Retrieval Approaches on Prediction of the Soil Organic Carbon", "description": "This study was to compare the performance of the index-based and unmixing-based classification approaches as well as their integration on discrimination of the bare soil pixels on Sentinel-2 (S2) and Landsat 8-OLI (L08-OLI) single-date scenes from dry and green vegetation within four local agricultural sites, in the Czech Republic. In conclusion, classification of soil cover using the integrated approach led to more accurate extraction of bare soil and higher performance SOC prediction models, on both types of satellite data. Considering all approaches, results obtained on S2 data were more accurate than those delivered on L08-OLI.\u00a0 The manuscript is about to be submitted after the final approval of all authors.", "keywords": ["Linear spectral unmixing", "EJP SOIL", "STEROPES", "Spectral indices", "Soil organic carbon", "Soil cover classification", "Airborne and satellite data"], "contacts": [{"organization": "Khosravi, Vahid, Gholizadeh, Asa, Castaldi, Fabio, Saberioon, Mohammadmehdi, Chapman Agyeman, Prince, \u017d\u00ed\u017eala, Daniel, Kode\u0161ov\u00e1, Radka, Bor\u016fvka, Lubo\u0161,", "roles": ["creator"]}]}, "links": [{"href": "https://doi.org/10.2139/ssrn.5042274"}, {"rel": "self", "type": "application/geo+json", "title": "10.2139/ssrn.5042274", "name": "item", "description": "10.2139/ssrn.5042274", "href": "https://repository.soilwise-he.eu/cat/collections/metadata:main/items/10.2139/ssrn.5042274"}, {"rel": "collection", "type": "application/json", "title": "Collection", "name": "collection", "description": "Collection", "href": "https://repository.soilwise-he.eu/cat/collections/metadata:main"}], "time": {"date": "2024-01-01T00:00:00Z"}}, {"id": "10.3390/f12070902", "type": "Feature", "geometry": null, "properties": {"license": "Open Access", "updated": "2026-09-21T16:19:23Z", "type": "Journal Article", "created": "2021-07-12", "title": "Aboveground Biomass Estimation in Short Rotation Forest Plantations in Northern Greece Using ESA\u2019s Sentinel Medium-High Resolution Multispectral and Radar Imaging Missions", "description": "Plantations of fast-growing forest species such as black locust (Robinia Pseudoacacia) can contribute to energy transformation, mitigate industrial pollution, and restore degraded, marginal land. In this study, the synergistic use of Sentinel-2 and Sentinel-1 time series data is explored for modeling aboveground biomass (AGB) in black locust short-rotation plantations in northeastern Greece. Optimal modeling dates and EO sensor data are also identified through the analysis. Random forest (RF) models were originally developed using monthly Sentinel-2 spectral indices, while, progressively, monthly Sentinel-1 bands were incorporated in the statistical analysis. The highest accuracy was observed for the models generated using Sentinel-2 August composites (R2 = 0.52). The inclusion of Sentinel-1 bands in the spectral indices\uffe2\uff80\uff99 models had a negligible effect on modeling accuracy during the leaf-on period. The correlation and comparative performance of the spectral indices in terms of pairwise correlation with AGB varied among the phenophases of the forest plantations. Overall, the field-measured AGB in the forest plantations plots presented a higher correlation with the optical Sentinel-2 images. The synergy of Sentinel-1 and Sentinel-2 data proved to be a non-efficient approach for improving forest biomass RF models throughout the year within the geographical and environmental context of our study.
", "keywords": ["random forests", "13. Climate action", "optical", "AGB", "0211 other engineering and technologies", "spectral indices", "0401 agriculture", " forestry", " and fisheries", "04 agricultural and veterinary sciences", "02 engineering and technology", "seasonal", "15. Life on land", "optical", " SAR", " spectral indices", " AGB", " seasonal", " random forests", "SAR"]}, "links": [{"href": "http://www.mdpi.com/1999-4907/12/7/902/pdf"}, {"href": "https://www.mdpi.com/1999-4907/12/7/902/pdf"}, {"href": "https://doi.org/10.3390/f12070902"}, {"rel": "related", "href": "https://repository.soilwise-he.eu/cat/collections/metadata:main/items/Forests", "name": "related record", "description": "related record", "type": "application/json"}, {"rel": "self", "type": "application/geo+json", "title": "10.3390/f12070902", "name": "item", "description": "10.3390/f12070902", "href": "https://repository.soilwise-he.eu/cat/collections/metadata:main/items/10.3390/f12070902"}, {"rel": "collection", "type": "application/json", "title": "Collection", "name": "collection", "description": "Collection", "href": "https://repository.soilwise-he.eu/cat/collections/metadata:main"}], "time": {"date": "2021-07-11T00:00:00Z"}}, {"id": "10.5281/zenodo.14143563", "type": "Feature", "geometry": null, "properties": {"updated": "2026-09-21T16:20:33Z", "type": "Report", "created": "2024-12-09", "title": "Impact of Different Supervised Bare Soil Pixels Retrieval Approaches on Prediction of the Soil Organic Carbon", "description": "This study was to compare the performance of the index-based and unmixing-based classification approaches as well as their integration on discrimination of the bare soil pixels on Sentinel-2 (S2) and Landsat 8-OLI (L08-OLI) single-date scenes from dry and green vegetation within four local agricultural sites, in the Czech Republic. In conclusion, classification of soil cover using the integrated approach led to more accurate extraction of bare soil and higher performance SOC prediction models, on both types of satellite data. Considering all approaches, results obtained on S2 data were more accurate than those delivered on L08-OLI.\u00a0 The manuscript is about to be submitted after the final approval of all authors.", "keywords": ["Linear spectral unmixing", "EJP SOIL", "STEROPES", "Spectral indices", "Soil organic carbon", "Soil cover classification", "Airborne and satellite data"], "contacts": [{"organization": "Khosravi, Vahid, Gholizadeh, Asa, Castaldi, Fabio, Saberioon, Mohammadmehdi, Chapman Agyeman, Prince, \u017d\u00ed\u017eala, Daniel, Kode\u0161ov\u00e1, Radka, Bor\u016fvka, Lubo\u0161,", "roles": ["creator"]}]}, "links": [{"href": "https://doi.org/10.5281/zenodo.14143563"}, {"rel": "self", "type": "application/geo+json", "title": "10.5281/zenodo.14143563", "name": "item", "description": "10.5281/zenodo.14143563", "href": "https://repository.soilwise-he.eu/cat/collections/metadata:main/items/10.5281/zenodo.14143563"}, {"rel": "collection", "type": "application/json", "title": "Collection", "name": "collection", "description": "Collection", "href": "https://repository.soilwise-he.eu/cat/collections/metadata:main"}], "time": {"date": "2024-01-01T00:00:00Z"}}], "links": [{"rel": "self", "type": "application/geo+json", "title": "This document as GeoJSON", "href": "https://repository.soilwise-he.eu/cat/collections/metadata:main/items?keywords=spectral+indices&f=json", "hreflang": "en-US"}, {"rel": "alternate", "type": "text/html", "title": "This document as HTML", "href": "https://repository.soilwise-he.eu/cat/collections/metadata:main/items?keywords=spectral+indices&f=html", "hreflang": "en-US"}, {"rel": "collection", "type": "application/json", "title": "Collection URL", "href": "https://repository.soilwise-he.eu/cat/collections/metadata:main", "hreflang": "en-US"}, {"type": "application/geo+json", "rel": "first", "title": "items (first)", "href": "https://repository.soilwise-he.eu/cat/collections/metadata:main/items?keywords=spectral+indices&", "hreflang": "en-US"}, {"rel": "last", "type": "application/geo+json", "title": "items (last)", "href": "https://repository.soilwise-he.eu/cat/collections/metadata:main/items?keywords=spectral+indices&offset=5", "hreflang": "en-US"}], "numberMatched": 5, "numberReturned": 5, "distributedFeatures": [], "timeStamp": "2026-09-21T20:51:28.831777Z"}