Probabilistic coastal wetland mapping with integration of optical, SAR and hydro-geomorphic data through stacking ensemble machine learning model

Prasad, Pankaj; Loveson, Victor Joseph; Kotha, Mahender

doi:10.1016/j.ecoinf.2023.102273

Cited by 5 publications

(2 citation statements)

References 93 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…The selection of the five vegetation indices was based on the results of previous studies and chosen according to experience. The precise equations for computing the commonly used vegetation indices are provided in Table 1, where NDVI, GNDVI, EVI and NDVIre are all used to classify wetland vegetation [9,23,24]. GNDVI is more sensitive to chlorophyll than NDVI, which is favorable for capturing the information of wetland vegetation during the emergence period.…”

Section: Feature Fusion Of Spectral Features Vegetation Indices and P...mentioning

confidence: 99%

Vegetation Classification and Evaluation of Yancheng Coastal Wetlands Based on Random Forest Algorithm from Sentinel-2 Images

Wang,

Jin,

Dardanelli

2024

Remote Sensing

View full text Add to dashboard Cite

The identification of wetland vegetation is essential for environmental protection and management as well as for monitoring wetlands’ health and assessing ecosystem services. However, some limitations on vegetation classification may be related to remote sensing technology, confusion between plant species, and challenges related to inadequate data accuracy. In this paper, vegetation classification in the Yancheng Coastal Wetlands is studied and evaluated from Sentinel-2 images based on a random forest algorithm. Based on consistent time series from remote sensing observations, the characteristic patterns of the Yancheng Coastal Wetlands were better captured. Firstly, the spectral features, vegetation indices, and phenological characteristics were extracted from remote sensing images, and classification products were obtained by constructing a dense time series using a dataset based on Sentinel-2 images in Google Earth Engine (GEE). Then, remote sensing classification products based on the random forest machine learning algorithm were obtained, with an overall accuracy of 95.64% and kappa coefficient of 0.94. Four indicators (POP, SOS, NDVIre, and B12) were the main contributors to the importance of the weight analysis for all features. Comparative experiments were conducted with different classification features. The results show that the method proposed in this paper has better classification.

show abstract

Section: Feature Fusion Of Spectral Features Vegetation Indices and P...mentioning

confidence: 99%

Vegetation Classification and Evaluation of Yancheng Coastal Wetlands Based on Random Forest Algorithm from Sentinel-2 Images

Wang,

Jin,

Dardanelli

2024

Remote Sensing

View full text Add to dashboard Cite

show abstract

“…The study found that combining machine learning models using model combination techniques significantly improved the accuracy of disease severity prediction in chickpea crops with wilt resistance. A study by Prasad et al (2023) used earth observation data and an ensemble model, combining random forest (RF), support vector machine (SVM), and multivariate adaptive regression spline (MARS) models, to create a highly accurate wetland map. The ensemble model achieved an impressive 96% accuracy when cross-validated with field data and demonstrated the effectiveness of integrating multiple key variables for probabilistic wetland mapping, providing valuable insights for coastal area planning and sustainable development.…”

Section: Introductionmentioning

confidence: 99%

Quantifying effects of climate change and farmers' information demand on wheat yield in India: a deep learning approach with regional clustering

Godara,

Birthal,

Avinash

et al. 2024

Front. Sustain. Food Syst.

View full text Add to dashboard Cite

IntroductionWith increasing demand for food and changing environmental conditions, a better understanding of the factors impacting wheat yield is essential for ensuring food security and sustainable agriculture. By analyzing the effect of multiple factors on wheat yield, the presented research provides novel insights into the potential impacts of climate change on wheat production in India. In the present study, datasets consisting of countrywide environmental and agronomic factors and wheat yield were collected. In addition, the study also analyzes the effect of information demand of farmers on production.MethodologyThe study employs a regional analysis approach by dividing the country into five zonal clusters: Northern Hills, Central India, Indo-Gangetic Plains, North-Eastern India, and Peninsular India. Correlation and Principal Component Analysis (PCA) were performed to uncover the month-wise key factors affecting wheat yield in each zone. Furthermore, four Machine Learning/Deep Learning-based models, including XGBoost, Multi-layer Perceptron (MLP), Gated Recurrent Unit (GRU), and 1-D Convolutional Neural Network (CNN), were developed to estimate wheat yield. This study estimated partial derivatives for all factors using Newton's Quotient Technique, a numerical method-based approach.ResultsThe analysis focused on applying this technique to the best-performing wheat yield estimation model, which was the GRU-based model (with RMSE and MAE of 0.60 t/ha and 0.46 t/ha, respectively).DiscussionIn the later sections of the article, multiple policy recommendations are communicated based on the extracted insights. The results of the presented research help inform decision-making regarding the development of strategies and policies to mitigate the impacts of climate change on wheat production in India.

show abstract

Integration Sentinel-1 SAR data and machine learning for land subsidence in-depth analysis in the North Coast of Central Java, Indonesia

Yananto,

Yulianto,

Wibowo

et al. 2024

Earth Sci Inform

View full text Add to dashboard Cite

Probabilistic coastal wetland mapping with integration of optical, SAR and hydro-geomorphic data through stacking ensemble machine learning model

Cited by 5 publications

References 93 publications

Vegetation Classification and Evaluation of Yancheng Coastal Wetlands Based on Random Forest Algorithm from Sentinel-2 Images

Vegetation Classification and Evaluation of Yancheng Coastal Wetlands Based on Random Forest Algorithm from Sentinel-2 Images

Quantifying effects of climate change and farmers' information demand on wheat yield in India: a deep learning approach with regional clustering

Integration Sentinel-1 SAR data and machine learning for land subsidence in-depth analysis in the North Coast of Central Java, Indonesia

Contact Info

Product

Resources

About