Using spectral diversity and heterogeneity measures to map habitat mosaics: An example from the Classical Karst

Kód výsledku v IS VaVaI

<a href="https://www.isvavai.cz/riv?ss=detail&h=RIV%2F60460709%3A41330%2F23%3A97751" target="_blank" >RIV/60460709:41330/23:97751 - isvavai.cz</a>

Výsledek na webu

<a href="http://dx.doi.org/10.1111/avsc.12762" target="_blank" >http://dx.doi.org/10.1111/avsc.12762</a>

DOI - Digital Object Identifier

<a href="http://dx.doi.org/10.1111/avsc.12762" target="_blank" >10.1111/avsc.12762</a>

Jazyk výsledku

angličtina

Název v původním jazyce

Using spectral diversity and heterogeneity measures to map habitat mosaics: An example from the Classical Karst

Popis výsledku v původním jazyce

QuestionsCan we map complex habitat mosaics from remote-sensing data? In doing this, are measures of spectral heterogeneity useful to improve image classification performance? Which measures are the most important? How can multitemporal data be integrated in a robust framework?LocationClassical Karst (NE Italy).MethodsFirst, a habitat map was produced from field surveys. Then, a collection of 12 monthly Sentinel-2 images was retrieved. Vegetation and spectral heterogeneity (SH) indices were computed and aggregated in four combinations: (1) monthly layers of vegetation and SH indices; (2) seasonal layers of vegetation and SH indices; (3) yearly layers of SH indices computed across the months; and (4) yearly layers of SH indices computed across the seasons. For each combination, a Random Forest classification was performed, first with the complete set of input layers and then with a subset obtained by recursive feature elimination. Training and validation points were independently extracted from field data.ResultsThe maximum overall accuracy (0.72) was achieved by using seasonally aggregated vegetation and SH indices, after the number of vegetation types was reduced by aggregation from 26 to 11. The use of SH measures significantly increased the overall accuracy of the classification. The spectral beta-diversity was the most important variable in most cases, while the spectral alpha-diversity and Rao's Q had a low relative importance, possibly because some habitat patches were small compared to the window used to compute the indices.ConclusionsThe results are promising and suggest that image classification frameworks could benefit from the inclusion of SH measures, rarely included before. Habitat mapping in complex landscapes can thus be improved in a cost- and time-effective way, suitable for monitoring applications. Mapping complex habitat mosaics from remote sensing is challenging. We tested whether the novel measures of spectral heterogeneity can improve image classification performances, comparing different combinations of vegetation and spectral heterogeneity indices. Spectral beta-diversity was one of the most important variables and the seasonal aggregation of images produced the highest accuracy.image

Název v anglickém jazyce

Using spectral diversity and heterogeneity measures to map habitat mosaics: An example from the Classical Karst

Popis výsledku anglicky

QuestionsCan we map complex habitat mosaics from remote-sensing data? In doing this, are measures of spectral heterogeneity useful to improve image classification performance? Which measures are the most important? How can multitemporal data be integrated in a robust framework?LocationClassical Karst (NE Italy).MethodsFirst, a habitat map was produced from field surveys. Then, a collection of 12 monthly Sentinel-2 images was retrieved. Vegetation and spectral heterogeneity (SH) indices were computed and aggregated in four combinations: (1) monthly layers of vegetation and SH indices; (2) seasonal layers of vegetation and SH indices; (3) yearly layers of SH indices computed across the months; and (4) yearly layers of SH indices computed across the seasons. For each combination, a Random Forest classification was performed, first with the complete set of input layers and then with a subset obtained by recursive feature elimination. Training and validation points were independently extracted from field data.ResultsThe maximum overall accuracy (0.72) was achieved by using seasonally aggregated vegetation and SH indices, after the number of vegetation types was reduced by aggregation from 26 to 11. The use of SH measures significantly increased the overall accuracy of the classification. The spectral beta-diversity was the most important variable in most cases, while the spectral alpha-diversity and Rao's Q had a low relative importance, possibly because some habitat patches were small compared to the window used to compute the indices.ConclusionsThe results are promising and suggest that image classification frameworks could benefit from the inclusion of SH measures, rarely included before. Habitat mapping in complex landscapes can thus be improved in a cost- and time-effective way, suitable for monitoring applications. Mapping complex habitat mosaics from remote sensing is challenging. We tested whether the novel measures of spectral heterogeneity can improve image classification performances, comparing different combinations of vegetation and spectral heterogeneity indices. Spectral beta-diversity was one of the most important variables and the seasonal aggregation of images produced the highest accuracy.image

Druh

J_imp - Článek v periodiku v databázi Web of Science

CEP obor

—

OECD FORD obor

10611 - Plant sciences, botany

Projekt

—

Návaznosti

S - Specificky vyzkum na vysokych skolach

Rok uplatnění

2023

Kód důvěrnosti údajů

S - Úplné a pravdivé údaje o projektu nepodléhají ochraně podle zvláštních právních předpisů

Název periodika

Applied Vegetation Science

ISSN

1402-2001

e-ISSN

1402-2001

Svazek periodika

26

Číslo periodika v rámci svazku

4

Stát vydavatele periodika

SE - Švédské království

Počet stran výsledku

14

Strana od-do

1-14

Kód UT WoS článku

001131498800001

EID výsledku v databázi Scopus

2-s2.0-85181197950