BIHAMTA TOOSI N., SAFIANIAN A., FAKHERAN S., POURMANAFI S., GINZLER C., WASER L., Global Ecology and Conservation, Vol. 19, PP. 1_16, 2019.

Abstract:

Mangrove forests in Iran are highly productive and complex ecosystems since theyrepresent the interface between land and sea. They are a unique environment for sup-porting biodiversity, and they provide direct and indirect benefits to humans. Investigatingchanges in mangrove forests is essential for ecologists and forest managers to improve theassessment and conservation of natural ecosystems. The goals of the present studyinclude: (I) to evaluate and compare four supervised classification algorithms based onLandsat time series imagery to detect mangrove cover in southern Iran, (II) to detectchanges in mangrove cover between 1985, 1998, and 2017; and (III) to compare the fourdifferent predictions resulting from the applied classification algorithms. An accuracyassessment was conducted using k-fold cross-validation and independent validation, anddifferences between the classification techniques were analyzed. Although all four algo-rithms produced high overall accuracy (ranging from 81% to 93%) and Kappa values (from0.81 to 0.92), visual comparisons of the predictions revealed that Random Forest (RF)performed best. The results of the change analysis showed that mangrove cover areasdecreased by approximately 4% from 1985 to 1998 and then increased by approximately8.9% from 1998 to 2017. A change detection map shows a decrease in mangrove cover innear coastal regions, such as the Tabl and Gavarzin areas, and an increase in mangrovecover at a distance from the Qeshm coastline that involves open spaces between the trees.Rising water levels and human development are important factors in the decline ofmangroves. Thefindings of this research are useful for the management, restoration andconservation planning of mangrove forest in southern Iran.