FRINK Linked Data Fragments server

Matches in SemOpenAlex for { <https://semopenalex.org/work/W4306175039> ?p ?o ?g. }

• W4306175039 endingPage "100849" @default.
• W4306175039 startingPage "100849" @default.
• W4306175039 abstract "Southern African countries are susceptible to recurrent droughts which enhance forest degradation and destructive pest outbreaks, which then significantly hinder the productivity of these forests. It is understood that drought impacts could be experienced within high rainfall regions and at a plantation level. However, very few studies have analyzed droughts within a plantation level in humid subtropical regions. Hence, there is a demand for efficient methods of analyzing droughts and the impacts they impose on forest vegetation within catchments that receive high rainfall. This study utilized a Kernel-support vector machine (SVM), random forests (RF), rotation forests (RTF) and extreme gradient boosting (XGBoost) to classify drought-damaged trees. The 2013 to 2017 study period is inclusive of the intense and prolonged 2015–2016 drought experienced in Southern Africa. The algorithms were employed on the vegetation moisture condition index (VMCI), vegetation condition index (VCI), normalized vegetation index (NDVI) and normalized difference water index (NDWI) derived from Landsat 4 and 5, 7 and 8 imageries. Results showed that all four algorithms were capable of effectively detecting trees that exhibit drought damage, especially RF and RTF and when classifying using conditional drought indices. This was based on the accuracy achieved by these algorithms where RTF and RF both achieved an overall accuracy (OA) of 96.30%, which was better than Kernel-SVM's 94.44% and the XGBoost's 90.74%. Overall, the study demonstrated that machine learning algorithms (MLAs), conditional drought indices and Landsat data could be used to classify drought damage on commercial forest vegetation within a high rainfall catchment." @default.
• W4306175039 created "2022-10-14" @default.
• W4306175039 creator A5015781547 @default.
• W4306175039 creator A5019450005 @default.
• W4306175039 creator A5036116007 @default.
• W4306175039 creator A5059044690 @default.
• W4306175039 date "2022-11-01" @default.
• W4306175039 modified "2023-09-27" @default.
• W4306175039 title "Localizing the analysis of drought impacts on KwaZulu-Natal's commercial forests" @default.
• W4306175039 cites W1569008196 @default.
• W4306175039 cites W1683156614 @default.
• W4306175039 cites W1901616594 @default.
• W4306175039 cites W1964571746 @default.
• W4306175039 cites W1972236369 @default.
• W4306175039 cites W1978617972 @default.
• W4306175039 cites W1995442241 @default.
• W4306175039 cites W1996061706 @default.
• W4306175039 cites W2001547114 @default.
• W4306175039 cites W2004456798 @default.
• W4306175039 cites W2028240797 @default.
• W4306175039 cites W2028334803 @default.
• W4306175039 cites W2029572886 @default.
• W4306175039 cites W2038541098 @default.
• W4306175039 cites W2054412564 @default.
• W4306175039 cites W2069267948 @default.
• W4306175039 cites W2083715815 @default.
• W4306175039 cites W2085282193 @default.
• W4306175039 cites W2085894056 @default.
• W4306175039 cites W2100176513 @default.
• W4306175039 cites W2113429172 @default.
• W4306175039 cites W2115521437 @default.
• W4306175039 cites W2125325727 @default.
• W4306175039 cites W2130627644 @default.
• W4306175039 cites W2144014687 @default.
• W4306175039 cites W2150757437 @default.
• W4306175039 cites W2152406914 @default.
• W4306175039 cites W2162921856 @default.
• W4306175039 cites W2261059368 @default.
• W4306175039 cites W2293006232 @default.
• W4306175039 cites W2317516903 @default.
• W4306175039 cites W2339685151 @default.
• W4306175039 cites W2346766736 @default.
• W4306175039 cites W2463979186 @default.
• W4306175039 cites W2473924042 @default.
• W4306175039 cites W2530171175 @default.
• W4306175039 cites W2564039347 @default.
• W4306175039 cites W2570762839 @default.
• W4306175039 cites W2586821431 @default.
• W4306175039 cites W2602216144 @default.
• W4306175039 cites W2610503222 @default.
• W4306175039 cites W2611687595 @default.
• W4306175039 cites W2742225967 @default.
• W4306175039 cites W2752227530 @default.
• W4306175039 cites W2753311673 @default.
• W4306175039 cites W2782404771 @default.
• W4306175039 cites W2784208206 @default.
• W4306175039 cites W2789912683 @default.
• W4306175039 cites W2792986592 @default.
• W4306175039 cites W2793124519 @default.
• W4306175039 cites W2801774111 @default.
• W4306175039 cites W2803116794 @default.
• W4306175039 cites W2908956665 @default.
• W4306175039 cites W2911964244 @default.
• W4306175039 cites W2912981538 @default.
• W4306175039 cites W2916848715 @default.
• W4306175039 cites W2942004611 @default.
• W4306175039 cites W2953772517 @default.
• W4306175039 cites W2953891900 @default.
• W4306175039 cites W2955786086 @default.
• W4306175039 cites W2971143994 @default.
• W4306175039 cites W2979371817 @default.
• W4306175039 cites W2990507152 @default.
• W4306175039 cites W2993832485 @default.
• W4306175039 cites W3014372673 @default.
• W4306175039 cites W3034750607 @default.
• W4306175039 cites W3088753106 @default.
• W4306175039 cites W3092193721 @default.
• W4306175039 cites W3102476541 @default.
• W4306175039 cites W3111203725 @default.
• W4306175039 cites W3119706975 @default.
• W4306175039 cites W3126232929 @default.
• W4306175039 cites W3142764358 @default.
• W4306175039 cites W3173755594 @default.
• W4306175039 cites W3196552943 @default.
• W4306175039 cites W4206176493 @default.
• W4306175039 cites W4210612706 @default.
• W4306175039 cites W4220687320 @default.
• W4306175039 doi "https://doi.org/10.1016/j.rsase.2022.100849" @default.
• W4306175039 hasPublicationYear "2022" @default.
• W4306175039 type Work @default.
• W4306175039 citedByCount "0" @default.
• W4306175039 crossrefType "journal-article" @default.
• W4306175039 hasAuthorship W4306175039A5015781547 @default.
• W4306175039 hasAuthorship W4306175039A5019450005 @default.
• W4306175039 hasAuthorship W4306175039A5036116007 @default.
• W4306175039 hasAuthorship W4306175039A5059044690 @default.
• W4306175039 hasConcept C100970517 @default.
• W4306175039 hasConcept C110872660 @default.

• next