Regional soil organic matter mapping models based on the optimal time window, feature selection algorithm and Google Earth Engine DOI
Chong Luo, Xinle Zhang, Yihao Wang

et al.

Soil and Tillage Research, Journal Year: 2022, Volume and Issue: 219, P. 105325 - 105325

Published: Jan. 25, 2022

Language: Английский

Google Earth Engine Cloud Computing Platform for Remote Sensing Big Data Applications: A Comprehensive Review DOI Creative Commons
Meisam Amani, Arsalan Ghorbanian, Seyed Ali Ahmadi

et al.

IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing, Journal Year: 2020, Volume and Issue: 13, P. 5326 - 5350

Published: Jan. 1, 2020

Remote sensing (RS) systems have been collecting massive volumes of datasets for decades, managing and analyzing which are not practical using common software packages desktop computing resources. In this regard, Google has developed a cloud platform, called Earth Engine (GEE), to effectively address the challenges big data analysis. particular, platform facilitates processing geo over large areas monitoring environment long periods time. Although was launched in 2010 proved its high potential different applications, it fully investigated utilized RS applications until recent years. Therefore, study aims comprehensively explore aspects GEE including datasets, functions, advantages/limitations, various applications. For purpose, 450 journal articles published 150 journals between January May 2020 were studied. It observed that Landsat Sentinel extensively by users. Moreover, supervised machine learning algorithms, such as Random Forest, more widely applied image classification tasks. also employed broad range Land Cover/land Use classification, hydrology, urban planning, natural disaster, climate analyses, processing. generally number publications significantly increased during past few years, is expected will be users from fields resolve their challenges.

Language: Английский

Citations

818

Object-Oriented LULC Classification in Google Earth Engine Combining SNIC, GLCM, and Machine Learning Algorithms DOI Creative Commons
Andrea Tassi, Marco Vizzari

Remote Sensing, Journal Year: 2020, Volume and Issue: 12(22), P. 3776 - 3776

Published: Nov. 17, 2020

Google Earth Engine (GEE) is a versatile cloud platform in which pixel-based (PB) and object-oriented (OO) Land Use–Land Cover (LULC) classification approaches can be implemented, thanks to the availability of many state-of-art functions comprising various Machine Learning (ML) algorithms. OO approaches, including both object segmentation textural analysis, are still not common GEE environment, probably due difficulties existing concatenating proper functions, tuning parameters overcome computational limits. In this context, work aimed at developing testing an approach combining Simple Non-Iterative Clustering (SNIC) algorithm identify spatial clusters, Gray-Level Co-occurrence Matrix (GLCM) calculate cluster indices, two ML algorithms (Random Forest (RF) or Support Vector (SVM)) perform final classification. A Principal Components Analysis (PCA) applied main seven GLCM indices synthesize one band information used for The proposed implemented user-friendly, freely available code useful classification, (e.g., choose input bands, select algorithm, test scales) compare it with PB approach. accuracy classifications assessed visually through confusion matrices that relevant statistics (producer’s, user’s, overall (OA)). methodology was broadly tested 154 km2 study area, located Lake Trasimeno area (central Italy), using Landsat 8 (L8), Sentinel 2 (S2), PlanetScope (PS) data. selected considering its complex LULC mosaic mainly composed artificial surfaces, annual permanent crops, small lakes, wooded areas. tests produced interesting results on different datasets (OA: RF (L8 = 72.7%, S2 82%, PS 74.2), SVM 79.1%, 80.2%, 74.8%), 64%, 89.3%, 77.9), 70.4, 86.9%, 73.9)). broad application demonstrated very good reliability whole process, even though process resulted, sometimes, too demanding higher resolution data, resources.

Language: Английский

Citations

284

Google Earth Engine and Artificial Intelligence (AI): A Comprehensive Review DOI Creative Commons
Liping Yang,

Joshua Driscol,

Sarigai Sarigai

et al.

Remote Sensing, Journal Year: 2022, Volume and Issue: 14(14), P. 3253 - 3253

Published: July 6, 2022

Remote sensing (RS) plays an important role gathering data in many critical domains (e.g., global climate change, risk assessment and vulnerability reduction of natural hazards, resilience ecosystems, urban planning). Retrieving, managing, analyzing large amounts RS imagery poses substantial challenges. Google Earth Engine (GEE) provides a scalable, cloud-based, geospatial retrieval processing platform. GEE also access to the vast majority freely available, public, multi-temporal offers free cloud-based computational power for analysis. Artificial intelligence (AI) methods are enabling technology automating interpretation imagery, particularly on object-based domains, so integration AI into represents promising path towards operationalizing automated RS-based monitoring programs. In this article, we provide systematic review relevant literature identify recent research that incorporates GEE. We then discuss some major challenges integrating several priorities future research. developed interactive web application designed allow readers intuitively dynamically publications included review.

Language: Английский

Citations

155

Flooding and its relationship with land cover change, population growth, and road density DOI Creative Commons

Mahfuzur Rahman,

Chen Ningsheng,

Golam Iftekhar Mahmud

et al.

Geoscience Frontiers, Journal Year: 2021, Volume and Issue: 12(6), P. 101224 - 101224

Published: May 5, 2021

Bangladesh experiences frequent hydro-climatic disasters such as flooding. These are believed to be associated with land use changes and climate variability. However, identifying the factors that lead flooding is challenging. This study mapped flood susceptibility in northeast region of using Bayesian regularization back propagation (BRBP) neural network, classification regression trees (CART), a statistical model (STM) evidence belief function (EBF), their ensemble models (EMs) for three time periods (2000, 2014, 2017). The accuracy machine learning algorithms (MLAs), STM, EMs were assessed by considering area under curve—receiver operating characteristic (AUC-ROC). Evaluation levels aforementioned revealed EM4 (BRBP-CART-EBF) outperformed (AUC > 90%) standalone other analyzed. Furthermore, this investigated relationships among cover change (LCC), population growth (PG), road density (RD), relative (RCF) areas period between 2000 2017. results showed very high increased 19.72% 2017, while PG rate 51.68% over same period. Pearson correlation coefficient RCF RD was calculated 0.496. findings highlight significant association floods causative factors. could valuable policymakers resource managers they can improvements management reduction damage risks.

Language: Английский

Citations

146

Mangrove Ecosystem Mapping Using Sentinel-1 and Sentinel-2 Satellite Images and Random Forest Algorithm in Google Earth Engine DOI Creative Commons
Arsalan Ghorbanian, Soheil Zaghian, Reza Mohammadi Asiyabi

et al.

Remote Sensing, Journal Year: 2021, Volume and Issue: 13(13), P. 2565 - 2565

Published: June 30, 2021

Mangroves are among the most productive ecosystems in existence, with many ecological benefits. Therefore, generating accurate thematic maps from mangrove is crucial for protecting, conserving, and reforestation planning these valuable natural resources. In this paper, Sentinel-1 Sentinel-2 satellite images were used synergy to produce a detailed ecosystem map of Hara protected area, Qeshm, Iran, at 10 m spatial resolution within Google Earth Engine (GEE) cloud computing platform. regard, 86 41 data, acquired 2019, employed generate seasonal optical synthetic aperture radar (SAR) features. Afterward, features inserted into pixel-based random forest (RF) classifier, resulting an average overall accuracy (OA) Kappa coefficient (KC) 93.23% 0.92, respectively, wherein all classes (except aerial roots) achieved high producer user accuracies over 90%. Furthermore, comprehensive quantitative qualitative assessments performed investigate robustness proposed approach, stable results through cross-validation consistency checks confirmed its applicability. It was revealed that integration multi-source remote sensing data contributed towards obtaining more reliable map. The approach relies on straightforward yet effective workflow mapping, rate automation can be easily implemented frequent precise mapping other parts world. Overall, further improve conservation sustainable management

Language: Английский

Citations

128

Evaluation and analysis of ecosystem service value based on land use/cover change in Dongting Lake wetland DOI Creative Commons

Xiangren Long,

Hui Lin,

Xuexian An

et al.

Ecological Indicators, Journal Year: 2022, Volume and Issue: 136, P. 108619 - 108619

Published: Feb. 2, 2022

Wetland vegetation has experienced significant loss and degradation over the last few decades. Although volumes of studies involve wetlands, limited attention been paid to long-term changes ecological values inland lake wetlands in China. In this paper, land use/cover data Dongting Lake wetland from 1995 2020 was generated based on Google Earth engine using Stacking algorithm. Subsequently, spatial temporal variation types explored dynamic analysis correlation indices change. The main factors influencing distribution were identified by Geodetector. Finally, degree impact ecosystem service value quantified equivalence factor method. results show that, past 25 years, use had switched with each other more frequently, a total 294.94 km2 area lost, mainly due shrinkage water, reeds sedge. affecting are population density, GDP, elevation sunshine duration, interaction drivers is mostly linearly enhanced no weakening effect. addition, showed trend first decreasing then increasing, ¥87,000.99 million ESV. study can provide basic information for preliminary work planning design, demonstrate importance ecosystems different regions. Based assessment results, it an important basis construction security patterns policy formulation civilization construction.

Language: Английский

Citations

128

Wildfire Damage Assessment over Australia Using Sentinel-2 Imagery and MODIS Land Cover Product within the Google Earth Engine Cloud Platform DOI Creative Commons
Seyd Teymoor Seydi, Mehdi Akhoondzadeh, Meisam Amani

et al.

Remote Sensing, Journal Year: 2021, Volume and Issue: 13(2), P. 220 - 220

Published: Jan. 10, 2021

Wildfires are major natural disasters negatively affecting human safety, ecosystems, and wildlife. Timely accurate estimation of wildfire burn areas is particularly important for post-fire management decision making. In this regard, Remote Sensing (RS) images great resources due to their wide coverage, high spatial temporal resolution, low cost. study, Australian affected by were estimated using Sentinel-2 imagery Moderate Resolution Imaging Spectroradiometer (MODIS) products within the Google Earth Engine (GEE) cloud computing platform. To end, a framework based on change analysis was implemented in two main phases: (1) producing binary map burned (i.e., vs. unburned); (2) estimating different Land Use/Land Cover (LULC) types. The first phase five steps: (i) preprocessing, (ii) spectral feature extraction pre-fire analyses; (iii) prediction detection differencing datasets; (iv) selection; (v) mapping selected features classifiers. second defining types LULC classes over global MODIS land cover product (MCD12Q1). Based test datasets, proposed showed potential detecting with an overall accuracy (OA) kappa coefficient (KC) 91.02% 0.82, respectively. It also observed that greatest area among related evergreen needle leaf forests burning rate 25 (%). Finally, results study good agreement Landsat products.

Language: Английский

Citations

112

DKDFN: Domain Knowledge-Guided deep collaborative fusion network for multimodal unitemporal remote sensing land cover classification DOI
Yansheng Li, Yuhan Zhou, Yongjun Zhang

et al.

ISPRS Journal of Photogrammetry and Remote Sensing, Journal Year: 2022, Volume and Issue: 186, P. 170 - 189

Published: Feb. 24, 2022

Language: Английский

Citations

96

Land use and land cover as a conditioning factor in landslide susceptibility: a literature review DOI Creative Commons
Renata Pacheco Quevedo, Andrés Velástegui-Montoya, Néstor Montalván-Burbano

et al.

Landslides, Journal Year: 2023, Volume and Issue: 20(5), P. 967 - 982

Published: Feb. 13, 2023

Abstract Landslide occurrence has become increasingly influenced by human activities. Accordingly, changing land use and cover (LULC) is an important conditioning factor in landslide susceptibility models. We present a bibliometric analysis review of how LULC was explored the context 536 scientific articles from 2001 to 2020. The pattern publications citations reveals that most hardly focus on relationship between landslides despite growing interest this topic. Most research outputs came Asian countries (some which are frequently affected landslides), mostly with prominent international collaboration. recognised three major themes regarding characteristics data, different simulated scenarios changes, role future for both susceptibility. studied classes included roads, soils (in broadest sense), forests, often approximate negative impacts expanding infrastructure, deforestation, or changes involving agricultural practice. highlight several concerned primarily current practice landslides. relevance slowly, though much potential be scenario close gaps many study areas.

Language: Английский

Citations

95

A Systematic Review on Advancements in Remote Sensing for Assessing and Monitoring Land Use and Land Cover Changes Impacts on Surface Water Resources in Semi-Arid Tropical Environments DOI Creative Commons
Makgabo Johanna Mashala, Timothy Dube, Bester Tawona Mudereri

et al.

Remote Sensing, Journal Year: 2023, Volume and Issue: 15(16), P. 3926 - 3926

Published: Aug. 8, 2023

This study aimed to provide a systematic overview of the progress made in utilizing remote sensing for assessing impacts land use and cover (LULC) changes on water resources (quality quantity). review also addresses research gaps, challenges, opportunities associated with remotely sensed data assessment monitoring. The applications monitoring LULC, along their quality quantity, has advanced significantly. availability high-resolution satellite imagery, integration multiple sensors, classification techniques have improved accuracy mapping change detection. Furthermore, highlights vast potential providing detailed information relationship between LULC through advancements science analytics, drones, web-based platforms, balloons. It emphasizes importance promoting efforts, spatial patterns, ecosystem services, hydrological models enables more comprehensive evaluation quantity changes. Continued technology methodologies will further improve our ability assess monitor ultimately leading informed decision making effective resource management. Such endeavors are crucial achieving sustainable management quantity.

Language: Английский

Citations

80