The study presents the analysis of the possible use of limited number of the Sentinel-2 and Sentinel-1 to check if crop declarations that the EU farmers submit to receive subsidies are true. The declarations used in the research were randomly divided into two independent sets (training and test). Based on the training set, supervised classification of both single images and their combinations was performed using random forest algorithm in SNAP (ESA) and our own Python scripts. A comparative accuracy analysis was performed on the basis of two forms of confusion matrix (full confusion matrix commonly used in remote sensing and binary confusion matrix used in machine learning) and various accuracy metrics (overall accuracy, accuracy, specificity, sensitivity, etc.). The highest overall accuracy (81%) was obtained in the simultaneous classification of multitemporal images (three Sentinel-2 and one Sentinel-1). An unexpectedly high accuracy (79%) was achieved in the classification of one Sentinel-2 image at the end of May 2018. Noteworthy is the fact that the accuracy of the random forest method trained on the entire training set is equal 80% while using the sampling method ca. 50%. Based on the analysis of various accuracy metrics, it can be concluded that the metrics used in machine learning, for example: specificity and accuracy, are always higher then the overall accuracy. These metrics should be used with caution, because unlike the overall accuracy, to calculate these metrics, not only true positives but also false positives are used as positive results, giving the impression of higher accuracy. Correct calculation of overall accuracy values is essential for comparative analyzes. Reporting the mean accuracy value for the classes as overall accuracy gives a false impression of high accuracy. In our case, the difference was 10–16% for the validation data, and 25–45% for the test data.
ABSTRACT:Digital photogrammetry and remote sensing solutions applied under the project and combined with the geographical information system made it possible to utilize data originating from various sources and dating back to different periods. Research works made use of archival and up-to-date aerial images, satellite images, orthophotomaps. Multitemporal data served for mapping and monitoring intermediate conditions of the Baltic Sea shore zone without a need for a direct interference in the environment. The main objective of research was to determine the dynamics and volume of sea shore changes along the selected part of coast in the period of 1951-2004, and to assess the tendencies of shore development in that area. For each of the six annual data sets, the following were determined: front dune base line, water line and the beach width. The location of the dune base line, which reflects the course of the shoreline in a given year was reconstructed based on stereoscopic study of images from each annual set. Unidirectional changes in the period of 1951-2004 occurred only within 10% of the examined shore section length. The examined shore is marked by a high and considerable dynamics of changes. Almost half of the shore, in particular the middle coast shows big changes, in excess of 2 m/year. The limits of shoreline changes ranged from 120 to -90 m, and their velocity from 0 to 11 m/year, save that the middle and west parts of the examined coast section were subjected to definitely more intense shore transformations. Research based on the analysis of multitemporal aerial images made it possible to reconstruct the intermediate conditions of the Baltic Sea shoreline and determine the volume and rate of changes in the location of dune base line in the examined period of 53 years, and to find out tendencies of shore development and dynamics.
BADANIA KORELACJI PIERWIASTKÓW ŚLADOWYCH W ŚRODOWISKU GLEBOWO -ROŚLINNYM PRZY ZASTOSOWANIU METOD GISCelem prezentowanego opracowania jest identyfikacja anomalnych koncentracji geochemicznych w glebach oraz korzeniu marchwi pochodzących z ogródków działkowych miasta Przemyśla. Przy zastosowaniu technik kartograficznych wykonano mapy monitoringu środowiska zanieczyszczeń, obejmujących rejestracje miejsc zakładów przemysłowych, wprowadzających wyznaczone pierwiastki śla-dowe do środowiska przyrodniczego. Technologie te umożliwiły również wizualizację interakcji zachodzących między systemem przyrodniczym typu gleba-roślina i wykonaniu map korelacji występującej w tym układzie. W ramach badań chemicznych, przy zastosowaniu atomowej spektroskopii absorpcyjnej (ASA), wyznaczono koncentrację kadmu, ołowiu i miedzi w roślinach oraz glebach. Badania mineralogiczne przy zastosowaniu dyfraktometrii rentgenowskiej oraz mikroskopii skenningowej, umożliwiły określenie składu fazowego badanych gleb. Wszystkie operacje i czynności związane z analizą przestrzenną i kartowaniem wykonane zostały w opensource`owym systemie QGIS/GRASS. Uzyskane wyniki badań chemicznych dla materiału roślinnego oraz gleb pozwalają stwierdzić, że we wszystkich 14 miejscach pomiarowych została przekroczona górna dopuszczalna granica zawartości Cd podawana w rozporządzeniu 420/211 komisji UE z 2011 roku. Zawartość Cu i Pb we wszystkich próbkach nie przekraczają dopuszczalnych norm. Mapy korelacji pomiędzy środowiskiem glebowym a roślinnym potwierdzają wyniki badań geochemicznych. Miejsca największej koncentracji kadmu pokrywają się z podwyższoną zawartością tego pierwiastka w roślinach.
scite is a Brooklyn-based organization that helps researchers better discover and understand research articles through Smart Citations–citations that display the context of the citation and describe whether the article provides supporting or contrasting evidence. scite is used by students and researchers from around the world and is funded in part by the National Science Foundation and the National Institute on Drug Abuse of the National Institutes of Health.
hi@scite.ai
10624 S. Eastern Ave., Ste. A-614
Henderson, NV 89052, USA
Copyright © 2024 scite LLC. All rights reserved.
Made with 💙 for researchers
Part of the Research Solutions Family.