Matches in SemOpenAlex for { <https://semopenalex.org/work/W3129454956> ?p ?o ?g. }
- W3129454956 endingPage "3776" @default.
- W3129454956 startingPage "3756" @default.
- W3129454956 abstract "Land-cover maps are important tools for monitoring large-scale environmental change and can be regularly updated using free satellite imagery data. A key challenge with constructing these maps is missing data in the satellite images on which they are based. To address this challenge, we created a Spatial Random Forest (S-RF) model that can accurately interpolate missing data in satellite images based on a modest training set of observed data in the image of interest. We demonstrate that this approach can be effective with only a minimal number of spatial covariates, namely latitude and longitude. The motivation for only using latitude and longitude in our model is that these covariates are available for all images whether the data are observed or missing due to cloud cover. The S-RF model can flexibly partition these covariates to provide accurate estimates, with easy incorporation of additional covariates to improve estimation if available. The effectiveness of our approach has been previously demonstrated for prediction of two land-cover classes in an Australian case study. In this paper, we extend the method to more than two classes. We demonstrate the performance of the S-RF method at interpolating multiple land-cover classes, using a case study drawn from South America. The results show that the method is best at predicting three land-cover classes, compared with 5 or 10 classes, and that other information is needed to improve performance as the number of classes grows, particularly if the classes are unbalanced. We explore two issues through a sensitivity analysis: the influence of the amount of missing data in the image and the influence of the amount of training data for model development and performance. The results show that the amount of missing data due to cloud cover is influential on model performance for multiple classes. We also found that increasing the amount of training data beyond 100,000 observations had minimal impact on model accuracy. Hence, a relatively small amount of observed data is required for training the model, which is beneficial for computation time." @default.
- W3129454956 created "2021-03-01" @default.
- W3129454956 creator A5001588690 @default.
- W3129454956 creator A5020121862 @default.
- W3129454956 creator A5032306186 @default.
- W3129454956 date "2021-02-14" @default.
- W3129454956 modified "2023-09-24" @default.
- W3129454956 title "Spatial Random Forest (S-RF): A random forest approach for spatially interpolating missing land-cover data with multiple classes" @default.
- W3129454956 cites W1517778786 @default.
- W3129454956 cites W1981213426 @default.
- W3129454956 cites W2001547114 @default.
- W3129454956 cites W2011500029 @default.
- W3129454956 cites W2014907398 @default.
- W3129454956 cites W2025741962 @default.
- W3129454956 cites W2028843131 @default.
- W3129454956 cites W2039476530 @default.
- W3129454956 cites W2085282193 @default.
- W3129454956 cites W2088557643 @default.
- W3129454956 cites W2092981979 @default.
- W3129454956 cites W2114828048 @default.
- W3129454956 cites W2114892242 @default.
- W3129454956 cites W2125325727 @default.
- W3129454956 cites W2135695572 @default.
- W3129454956 cites W2138408852 @default.
- W3129454956 cites W2261059368 @default.
- W3129454956 cites W2338318698 @default.
- W3129454956 cites W2544836728 @default.
- W3129454956 cites W2567087303 @default.
- W3129454956 cites W2742225967 @default.
- W3129454956 cites W2785717412 @default.
- W3129454956 cites W2900639982 @default.
- W3129454956 cites W2964822557 @default.
- W3129454956 cites W4252656192 @default.
- W3129454956 doi "https://doi.org/10.1080/01431161.2021.1881183" @default.
- W3129454956 hasPublicationYear "2021" @default.
- W3129454956 type Work @default.
- W3129454956 sameAs 3129454956 @default.
- W3129454956 citedByCount "4" @default.
- W3129454956 countsByYear W31294549562021 @default.
- W3129454956 countsByYear W31294549562022 @default.
- W3129454956 crossrefType "journal-article" @default.
- W3129454956 hasAuthorship W3129454956A5001588690 @default.
- W3129454956 hasAuthorship W3129454956A5020121862 @default.
- W3129454956 hasAuthorship W3129454956A5032306186 @default.
- W3129454956 hasBestOaLocation W31294549562 @default.
- W3129454956 hasConcept C114614502 @default.
- W3129454956 hasConcept C119043178 @default.
- W3129454956 hasConcept C119857082 @default.
- W3129454956 hasConcept C122523270 @default.
- W3129454956 hasConcept C123046963 @default.
- W3129454956 hasConcept C124101348 @default.
- W3129454956 hasConcept C127413603 @default.
- W3129454956 hasConcept C13280743 @default.
- W3129454956 hasConcept C146978453 @default.
- W3129454956 hasConcept C147176958 @default.
- W3129454956 hasConcept C154945302 @default.
- W3129454956 hasConcept C159620131 @default.
- W3129454956 hasConcept C169258074 @default.
- W3129454956 hasConcept C19269812 @default.
- W3129454956 hasConcept C205649164 @default.
- W3129454956 hasConcept C2778102629 @default.
- W3129454956 hasConcept C2780428219 @default.
- W3129454956 hasConcept C2780554747 @default.
- W3129454956 hasConcept C2780648208 @default.
- W3129454956 hasConcept C33923547 @default.
- W3129454956 hasConcept C41008148 @default.
- W3129454956 hasConcept C42812 @default.
- W3129454956 hasConcept C4792198 @default.
- W3129454956 hasConcept C58640448 @default.
- W3129454956 hasConcept C62649853 @default.
- W3129454956 hasConcept C78519656 @default.
- W3129454956 hasConcept C9357733 @default.
- W3129454956 hasConceptScore W3129454956C114614502 @default.
- W3129454956 hasConceptScore W3129454956C119043178 @default.
- W3129454956 hasConceptScore W3129454956C119857082 @default.
- W3129454956 hasConceptScore W3129454956C122523270 @default.
- W3129454956 hasConceptScore W3129454956C123046963 @default.
- W3129454956 hasConceptScore W3129454956C124101348 @default.
- W3129454956 hasConceptScore W3129454956C127413603 @default.
- W3129454956 hasConceptScore W3129454956C13280743 @default.
- W3129454956 hasConceptScore W3129454956C146978453 @default.
- W3129454956 hasConceptScore W3129454956C147176958 @default.
- W3129454956 hasConceptScore W3129454956C154945302 @default.
- W3129454956 hasConceptScore W3129454956C159620131 @default.
- W3129454956 hasConceptScore W3129454956C169258074 @default.
- W3129454956 hasConceptScore W3129454956C19269812 @default.
- W3129454956 hasConceptScore W3129454956C205649164 @default.
- W3129454956 hasConceptScore W3129454956C2778102629 @default.
- W3129454956 hasConceptScore W3129454956C2780428219 @default.
- W3129454956 hasConceptScore W3129454956C2780554747 @default.
- W3129454956 hasConceptScore W3129454956C2780648208 @default.
- W3129454956 hasConceptScore W3129454956C33923547 @default.
- W3129454956 hasConceptScore W3129454956C41008148 @default.
- W3129454956 hasConceptScore W3129454956C42812 @default.
- W3129454956 hasConceptScore W3129454956C4792198 @default.
- W3129454956 hasConceptScore W3129454956C58640448 @default.
- W3129454956 hasConceptScore W3129454956C62649853 @default.
- W3129454956 hasConceptScore W3129454956C78519656 @default.