BEGIN:VCALENDAR VERSION:2.0 PRODID:-//pretalx//talks.staging.osgeo.org//foss4g-europe-2024-academic-tra ck//talk//98XKEK BEGIN:VTIMEZONE TZID:EET BEGIN:STANDARD DTSTART:20000101T000000 RRULE:FREQ=YEARLY;BYMONTH=1;UNTIL=20001231T220000Z TZNAME:EET TZOFFSETFROM:+0200 TZOFFSETTO:+0200 END:STANDARD BEGIN:STANDARD DTSTART:20021027T050000 RRULE:FREQ=YEARLY;BYDAY=-1SU;BYMONTH=10 TZNAME:EET TZOFFSETFROM:+0300 TZOFFSETTO:+0200 END:STANDARD BEGIN:DAYLIGHT DTSTART:20020331T040000 RRULE:FREQ=YEARLY;BYDAY=-1SU;BYMONTH=3 TZNAME:EEST TZOFFSETFROM:+0200 TZOFFSETTO:+0300 END:DAYLIGHT END:VTIMEZONE BEGIN:VEVENT UID:pretalx-foss4g-europe-2024-academic-track-98XKEK@talks.staging.osgeo.or g DTSTART;TZID=EET:20240704T143000 DTEND;TZID=EET:20240704T150000 DESCRIPTION:It is well known that climate change impacts are increasingly a ffecting European territory\, often in the shape of extreme natural events . Among those\, in recent years\, heat waves due to global warming contrib uted to the acceleration of drying process. Particularly\, the Mediterrane an areas are expected to face extraordinary hot summer and increasingly fr equent drought events\, which may clearly affect the population. As a part ial confirmation of this forecast\, in between 2022 and 2023 Southern Euro pe was affected by lasting drought conditions\, which had several outcomes on the ecosystems. As an example\, in Po River (the longest Italian water stream) the worst water scarcity of the past two centuries was recorded ( Montanari et al.\, 2023). Experts agreed on the exceptionality of the phen omenon\, stating nevertheless the repeatability of such events in near fut ure (Bonaldo et al.\, 2022). Willing to face them\, local authorities expr essed the need of tools for monitoring the impacts of drought on rivers\, so to be capable of promptly enacting countermeasures.\nIn this context\, the authors partnered with Regione Lombardia for building a procedure orie nted at the exploitation of Copernicus Sentinel-1 (SAR) and Sentinel-2 (op tical) sensor fusion for water surface mapping\, applied in the case study of Po River (Conversi et al.\, 2023)\, based on supervised classification of combined optical and SAR imagery. The current work will present an evo lution of the proposed methodology\, which includes a considerable effort towards the full automation of the process\, a necessary step for making i t user friendly for public administration. \n\nThe designed procedure\, b uilt in Google Earth Engine\, is based on the combination of three images\ , namely the S-1 VV speckle filtered band (Level 1\, GRD) and the spectral indices Sentinel Water Mask and NDWI derived from S-2 (Level 1-C\, orthor ectified). Input imagery is selected to ensure complete coverage of the ar ea of interest\, with mosaicking if necessary images coming from different dates\, a reliable assumption considering that the drought is usually a s low phenomenon. The interval of time between images is anyway minimized by the code\, depending on data quality and availability. Training polygons are drawn by photointerpretation and then fed to a Random Forest-based sup ervised classifier\, jointly to the three aforementioned images. The outco me of the procedure is constituted by a map of water surface detected over the area of interest\, complemented with an estimate of the extent in km2 . Results are then validated and correlated with hydrometric records comin g from the field\, which corroborated the overall performance (Conversi et al.\, 2023).\n\nThis paper proposes an advancement in the methodology\, a imed at enhancing its usability by non-expert users\, so to set the base o f the development of a tool that can be exploited by local stakeholders. A n efficient automatic extraction of training samples\, is achieved by rand omly extracting the training set of pixels from a binary mask (water/non-w ater). \nThis water/non-water mask is derived by the combination of three sub-masks resulting from the automatic thresholding of the input imagery ( VV\, SWM\, NDWI)\, obtained with the Bmax Otsu algorithm (Markert et al.\, 2020). The water/non water mask includes only the pixels which have the s ame behavior for all input images and along the reference period.\nThe thr esholding procedure is automated using the concept of Otsu histogram-based algorithm for image segmentation. This methodology allows to define an op timal threshold value for distinguishing background and foreground objects . The inter-class variance is evaluated and the value that maximizes it is chosen\, thus maximizing the separability among pixel classes as well (Ot su\, 1979). A modified version of the algorithm\, the Bmax Otsu\, was expl oited\, which was originally developed for water detection through Sentine l-1. Otsu algorithm is indeed particularly effective in case of images cha racterized by a bimodal histogram of pixel values\, while Bmax Otsu is mor e suitable in presence of multiple classes or complex backgrounds (Markert et al.\, 2020)\, which is the case for the application presented in this work. The Bmax Otsu is based on a checkerboard subdivision of the origina l image\, on user-selected parameters. The maximum normalized Between-Clas s Variance (BCV) is evaluated in each cell of the checkerboard and sub-are as characterized by bimodality are selected for applying the Otsu algorith m\, thus leading to the goal threshold value (Markert et al.\, 2020).\nAs mentioned\, the outcomes of the Bmax Otsu procedure are exploited for extr acting random training samples for the machine learning-based classificati on algorithm. The best classification performance is obtained with a numbe r of pixels that corresponds to the 0.15% of the region of interest. \nThe validation was carried out with respect to another classification of the same area obtained with photo-interpreted training samples (Conversi et al .\, 2023)\, showing accuracies of the order of 80-90%. The automated versi on of the methodology for integrating optical and radar images in mapping river water surface then proved its effectiveness among several date inter vals taken as reference. \nAlthough the automation of the training sample selection slightly decreases the accuracy of the overall result with respe ct to the original approach\, the gain in terms of usability is invaluable . Indeed\, the elimination of the necessity for the user of photointerpret ing imagery and drawing polygons to train the classification algorithm rep resents a relevant step towards the realization of a standalone tool to be used by the public administration in real applications of river drought m onitoring. DTSTAMP:20260601T171935Z LOCATION:Omicum SUMMARY:Towards automation of river water surface detection - Stefano Conve rsi URL:https://talks.staging.osgeo.org/foss4g-europe-2024-academic-track/talk/ 98XKEK/ END:VEVENT END:VCALENDAR