Wetland Change Mapping Using Machine Learning Algorithms, and Their Link with Climate Variation and Economic Growth: A Case Study of Guangling County, China

Abstract

Wetlands are a distinctive terrestrial ecosystem that benefits living things, including people, in various ways. Sustainable wetland ecosystem resources are needed to protect the global environment. Wetlands in China have undergone positive and negative changes in response to several factors, but studies documenting their long-term dynamicity have been few, particularly in Guangling County. This study examines the change of wetlands area based on remotely sensed data while exploring trends associated with climate variations and economic growth in Guangling County, China. Analysis of remotely sensed imagery, mainly in hilly and nonhomogeneous environments is problematic, largely as a result of interference and their high spectral non-homogeneity. We conducted experiments using five classical machine learning algorithms based on the Google Earth Engine (GEE) and obtained the greatest robustness and accuracy using a Support Vector Machine (SVM)—Radial Basis Function (RBF) kernel approach, with overall accuracy and kappa statistics ranging from 86% to 98.1% and from 0.789 to 0.960, respectively. Based on the SVM-RBF model’s outperformance of four other algorithms, we identified spatial distributions of wetland in the study area and associated change trends. We found that 45.71 km2 of wetland area was lost over the past 3.7 decades (January 1984–December 2020), or 81.82% of wetland area coverage. In this paper, we explore how factors such as county economic growth (GDP), humidity, and temperature variations are tightly linked with wetland change.

Efficacy of the unmodified and modified water indices for saline wetland ecosystems

“…Wetland classification (Ahmed, Akter, Marandi, Schüth, & Environment, 2021) Analysis of surface water resources (Bhangale, More, Shaikh, Patil, & More, 2020) Water body extraction (Kaplan & Avdan, 2017) Assessing wetland habitat vulnerability (Pal & Paul, 2020) Land Use Land Cover (LULC) mapping (Chatziantoniou, Petropoulos, & Psomiadis, 2017) Wetland change mapping (Gemechu, Rui, & Lu, 2022) Monitoring drought (Amalo, Ma'rufah, & Permatasari, 2018)…”

A Random Forest-Based Multi-Index Classification (RaFMIC) Approach to Mapping Three-Decadal Inundation Dynamics in Dryland Wetlands Using Google Earth Engine

“…Multi-index classification (i.e., using multiple vegetation and water indices as input layers) allows to capture the complex vegetation and water response of wetlands effectively, compared to spectral band-based classification, while minimizing the effects of illumination conditions [33,42,43]. Machine learning methods have recently been employed by a number of researchers to map wetland inundation due to their robustness in capturing complex relationships between the datasets [44][45][46][47][48]. Here, the random forest works as a robust classification algorithm which is capable of capturing complex relationships between inputs (i.e., a range of spectral responses for the wet and dry surface areas) and outputs (i.e., wetland inundation), even with a small dataset [49].…”

Quantitative Evaluation of Psychological Tolerance under the Haze: A Case Study of Typical Provinces and Cities in China with Severe Haze

“…There are two kinds of sentiment analysis for microblog data: machine-learning algorithms and sentiment lexicon. It is very important in the fields of opinion judgment, information prediction, and artificial intelligence [ 15 , 16 ].…”