Vegetation Types Mapping Using Multi-Temporal Landsat Images in the Google Earth Engine Platform

Vegetation Types (VTs) are important managerial units, and their identification serves as essential tools for the conservation of land covers. Despite a long history of Earth observation applications to assess and monitor land covers, the quantitative detection of sparse VTs remains problematic, especially in arid and semiarid areas. This research aimed to identify appropriate multi-temporal datasets to improve the accuracy of VTs classification in a heterogeneous landscape in Central Zagros, Iran. To do so, first the Normalized Difference Vegetation Index (NDVI) temporal profile of each VT was identified in the study area for the period of 2018, 2019, and 2020. This data revealed strong seasonal phenological patterns and key periods of VTs separation. It led us to select the optimal time series images to be used in the VTs classification. We then compared single-date and multi-temporal datasets of Landsat 8 images within the Google Earth Engine (GEE) platform as the input to the Random Forest classifier for VTs detection. The single-date classification gave a median Overall Kappa (OK) and Overall Accuracy (OA) of 51% and 64%, respectively. Instead, using multi-temporal images led to an overall kappa accuracy of 74% and an overall accuracy of 81%. Thus, the exploitation of multi-temporal datasets favored accurate VTs classification. In addition, the presented results underline that available open access cloud-computing platforms such as the GEE facilitates identifying optimal periods and multitemporal imagery for VTs classification.

[1]  Yuei-An Liou,et al.  Land-Use Land-Cover Classification by Machine Learning Classifiers for Satellite Observations - A Review , 2020, Remote. Sens..

[2]  L. Macaulay,et al.  Applying ecological site concepts and state‐and‐transition models to a grazed riparian rangeland , 2018, Ecology and evolution.

[3]  Gregory S. Okin,et al.  Leveraging Google Earth Engine (GEE) and machine learning algorithms to incorporate in situ measurement from different times for rangelands monitoring , 2020 .

[4]  J. Kovacs,et al.  Extrapolating canopy phenology information using Sentinel-2 data and the Google Earth Engine platform to identify the optimal dates for remotely sensed image acquisition of semiarid mangroves. , 2020, Journal of environmental management.

[5]  Lukas W. Lehnert,et al.  Land Cover Classification using Google Earth Engine and Random Forest Classifier - The Role of Image Composition , 2020, Remote. Sens..

[6]  Xiaoping Liu,et al.  High-resolution multi-temporal mapping of global urban land using Landsat images based on the Google Earth Engine Platform , 2018 .

[7]  Ronny Richter,et al.  A multisensoral approach for high-resolution land cover and pasture degradation mapping in the humid tropics: A case study of the fragmented landscape of Rio de Janeiro , 2019, Int. J. Appl. Earth Obs. Geoinformation.

[8]  Weijia Li,et al.  Integrating Google Earth imagery with Landsat data to improve 30-m resolution land cover mapping , 2020 .

[9]  Emma Izquierdo-Verdiguier,et al.  Growing stock volume from multi-temporal landsat imagery through google earth engine , 2019, Int. J. Appl. Earth Obs. Geoinformation.

[10]  Michael E. Schaepman,et al.  Spatial monitoring of grassland management using multi-temporal satellite imagery , 2020, Ecological Indicators.

[11]  Mahdi Hasanlou,et al.  Improved land cover map of Iran using Sentinel imagery within Google Earth Engine and a novel automatic workflow for land cover classification using migrated training samples , 2020, ISPRS Journal of Photogrammetry and Remote Sensing.

[12]  Paul D Macintyre,et al.  Impact of ecological redundancy on the performance of machine learning classifiers in vegetation mapping , 2018, Ecology and evolution.

[13]  Zhengwei Yang,et al.  AgKit4EE: A toolkit for agricultural land use modeling of the conterminous United States based on Google Earth Engine , 2020, Environ. Model. Softw..

[14]  Yang Hu,et al.  Land Cover Changes and Their Driving Mechanisms in Central Asia from 2001 to 2017 Supported by Google Earth Engine , 2019, Remote. Sens..

[15]  Paula D. Blanco,et al.  cological site classification of semiarid rangelands : Synergistic use of andsat and Hyperion imagery , 2014 .

[16]  Haohuan Fu,et al.  Exploring the potential role of feature selection in global land-cover mapping , 2016 .

[17]  Erxue Chen,et al.  Classification of Land Cover, Forest, and Tree Species Classes with ZiYuan-3 Multispectral and Stereo Data , 2019, Remote. Sens..

[18]  Michael Dixon,et al.  Google Earth Engine: Planetary-scale geospatial analysis for everyone , 2017 .

[19]  R. Congalton,et al.  Automated cropland mapping of continental Africa using Google Earth Engine cloud computing , 2017 .

[20]  J. Karl,et al.  A hyper-temporal remote sensing protocol for high-resolution mapping of ecological sites , 2017, PloS one.

[21]  A. Huete,et al.  A Modified Soil Adjusted Vegetation Index , 1994 .

[22]  Mika Siljander,et al.  Auxiliary datasets improve accuracy of object-based land use/land cover classification in heterogeneous savanna landscapes , 2019, Remote Sensing of Environment.

[23]  Xiao Zhang,et al.  A SPECLib-based operational classification approach: A preliminary test on China land cover mapping at 30 m , 2018, Int. J. Appl. Earth Obs. Geoinformation.

[24]  T. Higginbottom,et al.  Machine learning and multi-sensor based modelling of woody vegetation in the Molopo Area, South Africa , 2019, Remote Sensing of Environment.

[25]  Luca Pipia,et al.  Green LAI Mapping and Cloud Gap-Filling Using Gaussian Process Regression in Google Earth Engine , 2021, Remote. Sens..

[26]  Ladislav Mucina,et al.  Efficacy of multi-season Sentinel-2 imagery for compositional vegetation classification , 2020, Int. J. Appl. Earth Obs. Geoinformation.

[27]  Isabel Luisa Castillejo-González,et al.  Combining Object-Based Image Analysis with Topographic Data for Landform Mapping: A Case Study in the Semi-Arid Chaco Ecosystem, Argentina , 2019, ISPRS Int. J. Geo Inf..

[28]  El Mostafa Bachaoui,et al.  Crop type mapping from pansharpened Landsat 8 NDVI data: A case of a highly fragmented and intensive agricultural system , 2018, Remote Sensing Applications: Society and Environment.

[29]  A. Huete,et al.  A 30-m landsat-derived cropland extent product of Australia and China using random forest machine learning algorithm on Google Earth Engine cloud computing platform , 2018, ISPRS Journal of Photogrammetry and Remote Sensing.

[30]  Anssi Pekkarinen,et al.  Participatory mapping of forest plantations with Open Foris and Google Earth Engine , 2019, ISPRS Journal of Photogrammetry and Remote Sensing.

[31]  Xiaohui Yang,et al.  Land use/cover classification in an arid desert-oasis mosaic landscape of China using remote sensed imagery: Performance assessment of four machine learning algorithms , 2020, Global Ecology and Conservation.

[32]  Nengcheng Chen,et al.  Mapping Paddy Rice Fields by Combining Multi-Temporal Vegetation Index and Synthetic Aperture Radar Remote Sensing Data Using Google Earth Engine Machine Learning Platform , 2020, Remote. Sens..

[33]  Dirk Pflugmacher,et al.  Mapping pan-European land cover using Landsat spectral-temporal metrics and the European LUCAS survey , 2019, Remote Sensing of Environment.

[34]  Jochem Verrelst,et al.  Classification of Plant Ecological Units in Heterogeneous Semi-Steppe Rangelands: Performance Assessment of Four Classification Algorithms , 2021, Remote. Sens..

[35]  Laurence Hubert-Moy,et al.  Evaluation of Sentinel-2 time-series for mapping floodplain grassland plant communities , 2019, Remote Sensing of Environment.

[36]  Le Yu,et al.  A multiple dataset approach for 30-m resolution land cover mapping: a case study of continental Africa , 2018 .