Global Estimation of Biophysical Variables from Google Earth Engine Platform

Exploring evolution characteristics of eco-environment quality in the Yangtze River Basin based on remote sensing ecological index

As an important ecological-economic development area in China, scientific understanding of the spatial and temporal changes in eco-environment quality (EEQ) and its drivers in the Yangtze River Basin (YRB) is crucial for the effective implementation of ecological protection projects in the YRB. To address the lack of large-scale EEQ assessment in the YRB, this paper uses the Google Earth Engine (GEE) platform and the Remote Sensing Ecological Index (RSEI) to investigate the spatial and temporal characteristics of EEQ in the YRB from 2000 to 2020, and to analyze the impact of various factors on the EEQ of the YRB. This study showed that: (1) The overall EEQ of YRB was at the 'good' grade over the past 20 years, showing an increasing trend, with the value changing from 0.70 to 0.77. (2) The YRB's EEQ has positive spatial aggregation characteristics, with the northern part of the Jialing River basin and the Han River basin exhibiting a high-high aggregation type and the upper reaches exhibiting a low-low aggregation type. (3) In the past 20 years, the human activities had a greater impact on the EEQ of the YRB; moreover, all factors had a greater impact on the EEQ than a single factor. The interaction between the biological abundance index and population density had the most effect, with a q-value of 0.737 in 2020.

ICESat-2 for Canopy Cover Estimation at Large-Scale on a Cloud-Based Platform

Forest canopy cover is an essential biophysical parameter of ecological significance, especially for characterizing woodlands and forests. This research focused on using data from the ICESat-2/ATLAS spaceborne lidar sensor, a photon-counting altimetry system, to map the forest canopy cover over a large country extent. The study proposed a novel approach to compute categorized canopy cover using photon-counting data and available ancillary Landsat images to build the canopy cover model. In addition, this research tested a cloud-mapping platform, the Google Earth Engine (GEE), as an example of a large-scale study. The canopy cover map of the Republic of Türkiye produced from this study has an average accuracy of over 70%. Even though the results were promising, it has been determined that the issues caused by the auxiliary data negatively affect the overall success. Moreover, while GEE offered many benefits, such as user-friendliness and convenience, it had processing limits that posed challenges for large-scale studies. Using weak or strong beams' segments separately did not show a significant difference in estimating canopy cover. Briefly, this study demonstrates the potential of using photon-counting data and GEE for mapping forest canopy cover at a large scale.

Google earth engine based computational system for the earth and environment monitoring applications during the COVID-19 pandemic using thresholding technique on SAR datasets

Observing the earth and environmental conditions during the COVID-19 pandemic lockdown along with travel restrictions headed to worse circumstance. These scenarios amplified the hurdles of flood management. In order to resolves these issues, an efficient and resilient geospatial framework with unconventional systems is also required for the generation of instantaneous results. Hence to avoid these deficiencies, the google earth engine based computational system integrated with analytical tools for large-scale data handling is introduced for the earth and environmental monitoring applications. The present study proposes a working model for geospatial data processing to understand socio-demographic implications with a web-based analytical interface. The research introduces a histogram-based thresholding approach for real-time surface water mapping along with precise data processing and analysis for automated monitoring. The study integrates geospatial datasets to a enhanced data processing methods in a web-based platform to deliver the required results for extensive planning and decision making. Furthermore, a similar type of work can be undertaken for other disaster management applications.

A Review of Hybrid Approaches for Quantitative Assessment of Crop Traits Using Optical Remote Sensing: Research Trends and Future Directions

Remote sensing technology allows to provide information about biochemical and biophysical crop traits and monitor their spatiotemporal dynamics of agriculture ecosystems. Among multiple retrieval techniques, hybrid approaches have been found to provide outstanding accuracy, for instance, for the inference of leaf area index (LAI), fractional vegetation cover (fCover), and leaf and canopy chlorophyll content (LCC and CCC). The combination of radiative transfer models (RTMs) and data-driven models creates an advantage in the use of hybrid methods. Through this review paper, we aim to provide state-of-the-art hybrid retrieval schemes and theoretical frameworks. To achieve this, we reviewed and systematically analyzed publications over the past 22 years. We identified two hybrid-based parametric and hybrid-based nonparametric regression models and evaluated their performance for each variable of interest. From the results of our extensive literature survey, most research directions are now moving towards combining RTM and machine learning (ML) methods in a symbiotic manner. In particular, the development of ML will open up new ways to integrate innovative approaches such as integrating shallow or deep neural networks with RTM using remote sensing data to reduce errors in crop trait estimations and improve control of crop growth conditions in very large areas serving precision agriculture applications.

Google Earth Engine and Artificial Intelligence (AI): A Comprehensive Review

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

Gaussian processes retrieval of crop traits in Google Earth Engine based on Sentinel-2 top-of-atmosphere data

The unprecedented availability of optical satellite data in cloud-based computing platforms, such as Google Earth Engine (GEE), opens new possibilities to develop crop trait retrieval models from the local to the planetary scale. Hybrid retrieval models are of interest to run in these platforms as they combine the advantages of physically- based radiative transfer models (RTM) with the flexibility of machine learning regression algorithms. Previous research with GEE primarily relied on processing bottom-of-atmosphere (BOA) reflectance data, which requires atmospheric correction. In the present study, we implemented hybrid models directly into GEE for processing Sentinel-2 (S2) Level-1C (L1C) top-of-atmosphere (TOA) reflectance data into crop traits. To achieve this, a training dataset was generated using the leaf-canopy RTM PROSAIL in combination with the atmospheric model 6SV. Gaussian process regression (GPR) retrieval models were then established for eight essential crop traits namely leaf chlorophyll content, leaf water content, leaf dry matter content, fractional vegetation cover, leaf area index (LAI), and upscaled leaf variables (i.e., canopy chlorophyll content, canopy water content and canopy dry matter content). An important pre-requisite for implementation into GEE is that the models are sufficiently light in order to facilitate efficient and fast processing. Successful reduction of the training dataset by 78% was achieved using the active learning technique Euclidean distance-based diversity (EBD). With the EBD-GPR models, highly accurate validation results of LAI and upscaled leaf variables were obtained against in situ field data from the validation study site Munich-North-Isar (MNI), with normalized root mean square errors (NRMSE) from 6% to 13%. Using an independent validation dataset of similar crop types (Italian Grosseto test site), the retrieval models showed moderate to good performances for canopy-level variables, with NRMSE ranging from 14% to 50%, but failed for the leaf-level estimates. Obtained maps over the MNI site were further compared against Sentinel-2 Level 2 Prototype Processor (SL2P) vegetation estimates generated from the ESA Sentinels' Application Platform (SNAP) Biophysical Processor, proving high consistency of both retrievals (R ² from 0.80 to 0.94). Finally, thanks to the seamless GEE processing capability, the TOA-based mapping was applied over the entirety of Germany at 20 m spatial resolution including information about prediction uncertainty. The obtained maps provided confidence of the developed EBD-GPR retrieval models for integration in the GEE framework and national scale mapping from S2-L1C imagery. In summary, the proposed retrieval workflow demonstrates the possibility of routine processing of S2 TOA data into crop traits maps at any place on Earth as required for operational agricultural applications.

Monitoring migratory birds of India's largest shallow saline Ramsar site (Sambhar Lake) using geospatial data for wetland restoration

Globally, saline lakes occupy about 23% by area, and 44% by volume. Importantly, these lakes might desiccate by 2025 due to agricultural diversion, illegal encroachment, or modify due to pollution, and invasive species. India's largest saline lake, Sambhar is currently shrinking at a phenomenal rate of 4.23% every decade due to illegal saltpan encroachments. This study aims to identify the trend of migratory birds and monthly wetland status. Birds' survey was conducted for 2019, 2020 and 2021, and combined it with literature data of 1994, 2003, and 2013, for understanding their visiting trends, feeding habits, migratory and resident birds ratio, along with ecological diversity index analysis. Normalized Difference Water Index (NDWI) was scripted in Google Earth Engine. Results state that lake has been suitable for 97 species. Highest NDWI values was 0.71 in 2021 and lowest 0.008 in 2019. Notably, the decreasing trend of migratory birds coupled with decreasing water level indicates the dubious status for its existence. If these causal factors are not checked, it might completely desiccate. Authors recommend a few steps that might help conservation. Least, the cost of restoration might exceed the revenue generation.

SUPPLEMENTARY INFORMATION

The online version contains supplementary material available at 10.1007/s11273-022-09875-3.

Mapping Land Cover Types for Highland Andean Ecosystems in Peru Using Google Earth Engine

Highland Andean ecosystems sustain high levels of floral and faunal biodiversity in areas with diverse topography and provide varied ecosystem services, including the supply of water to cities and downstream agricultural valleys. Google (™) has developed a product specifically designed for mapping purposes (Earth Engine), which enables users to harness the computing power of a cloud-based solution in near-real time for land cover change mapping and monitoring. We explore the feasibility of using this platform for mapping land cover types in topographically complex terrain with highly mixed vegetation types (Nor Yauyos Cochas Landscape Reserve located in the central Andes of Peru) using classification machine learning (ML) algorithms in combination with different sets of remote sensing data. The algorithms were trained using 3601 sampling pixels of (a) normalized spectral bands between the visible and near infrared spectrum of the Landsat 8 OLI sensor for the 2018 period, (b) spectral indices of vegetation, soil, water, snow, burned areas and bare ground and (c) topographic-derived indices (elevation, slope and aspect). Six ML algorithms were tested, including CART, random forest, gradient tree boosting, minimum distance, naïve Bayes and support vector machine. The results reveal that ML algorithms produce accurate classifications when spectral bands are used in conjunction with topographic indices, resulting in better discrimination among classes with similar spectral signatures such as pajonal (tussock grass-dominated cover) and short grasses or rocky groups, and moraines, agricultural and forested areas. The model with the highest explanatory power was obtained from the combination of spectral bands and topographic indices using the random forest algorithm (Kappa = 0.81). Our study presents a first approach of its kind in topographically complex Cordilleran terrain and we show that GEE is particularly useful in large-scale land cover mapping and monitoring in mountainous ecosystems subject to rapid changes and conversions, with replicability and scalability to other areas with similar characteristics.

Quantifying Fundamental Vegetation Traits over Europe Using the Sentinel-3 OLCI Catalogue in Google Earth Engine

Thanks to the emergence of cloud-computing platforms and the ability of machine learning methods to solve prediction problems efficiently, this work presents a workflow to automate spatiotemporal mapping of essential vegetation traits from Sentinel-3 (S3) imagery. The traits included leaf chlorophyll content (LCC), leaf area index (LAI), fraction of absorbed photosynthetically active radiation (FAPAR), and fractional vegetation cover (FVC), being fundamental for assessing photosynthetic activity on Earth. The workflow involved Gaussian process regression (GPR) algorithms trained on top-of-atmosphere (TOA) radiance simulations generated by the coupled canopy radiative transfer model (RTM) SCOPE and the atmospheric RTM 6SV. The retrieval models, named to S3-TOA-GPR-1.0, were directly implemented in Google Earth Engine (GEE) to enable the quantification of the traits from TOA data as acquired from the S3 Ocean and Land Colour Instrument (OLCI) sensor.Following good to high theoretical validation results with normalized root mean square error (NRMSE) ranging from 5% (FAPAR) to 19% (LAI), a three fold evaluation approach over diverse sites and land cover types was pursued: (1) temporal comparison against LAI and FAPAR products obtained from Moderate Resolution Imaging Spectroradiometer (MODIS) for the time window 2016-2020, (2) spatial difference mapping with Copernicus Global Land Service (CGLS) estimates, and (3) direct validation using interpolated in situ data from the VALERI network. For all three approaches, promising results were achieved. Selected sites demonstrated coherent seasonal patterns compared to LAI and FAPAR MODIS products, with differences between spatially averaged temporal patterns of only 6.59%. In respect of the spatial mapping comparison, estimates provided by the S3-TOA-GPR-1.0 models indicated highest consistency with FVC and FAPAR CGLS products. Moreover, the direct validation of our S3-TOA-GPR-1.0 models against VALERI estimates indicated with regard to jurisdictional claims in good retrieval performance for LAI, FAPAR and FVC. We conclude that our retrieval workflow of spatiotemporal S3 TOA data processing into GEE opens the path towards global monitoring of fundamental vegetation traits, accessible to the whole research community.

Time Series of Quad-Pol C-Band Synthetic Aperture Radar for the Forecasting of Crop Biophysical Variables of Barley Fields Using Statistical Techniques

This paper aims to both fit and predict crop biophysical variables with a SAR image series by performing a factorial experiment and estimating time series models using a combination of forecasts. Two plots of barley grown under rainfed conditions in Spain were monitored during the growing cycle of 2015 (February to June). The dataset included nine field estimations of agronomic parameters, 20 RADARSAT-2 images, and daily weather records. Ten polarimetric observables were retrieved and integrated to derive the six agronomic and monitoring variables, including the height, biomass, fraction of vegetation cover, leaf area index, water content, and soil moisture. The statistical methods applied, namely double smoothing, ARIMAX, and robust regression, allowed the adjustment and modelling of these field variables. The model equations showed a positive contribution of meteorological variables and a strong temporal component in the crop’s development, as occurs in natural conditions. After combining different models, the results showed the best efficiency in terms of forecasting and the influence of several weather variables. The existence of a cointegration relationship between the data series of the same crop in different fields allows for adjusting and predicting the results in other fields with similar crops without re-modelling.

Impacts of droughts and floods on croplands and crop production in Southeast Asia - An application of Google Earth Engine

While droughts and floods have intensified in recent years, only a handful of studies have assessed their impacts on croplands and production in Southeast Asia. Here, we used the Google Earth Engine to assess the droughts and floods and their impacts on croplands and crop production over 40 years from 1980 to 2019. Using the Palmer Drought Severity Index (PDSI) as the basis for determining the drought and flood levels, and crop damage levels, crop production loss in both the Monsoon Climate Region (MCR) and the Equatorial Climate Region (ECR) of Southeast Asia was assessed over 47,192 grid points with 10 × 10-kilometer resolution. We found that rainfed crops were severely affected by droughts in the MCR and floods in the ECR. About 9.42 million ha and 3.72 million ha of cropland was damaged by droughts and floods, respectively. We estimated a total loss of 20.64 million tons of crop production between 2015 and 2019. Rainfed crops in Thailand, Cambodia, and Myanmar were strongly affected by droughts, whereas Indonesia, the Philippines, and Malaysia were more affected by floods over the same period. Accordingly, four levels of policy interventions were prioritized by considering the geolocated crop damage levels.

Assessment of the Spatial and Temporal Patterns of Cover Crops Using Remote Sensing

Cover cropping is a conservation practice that helps to alleviate soil health problems and reduce nutrient losses. Understanding the spatial variability in historic and current adoption of cover cropping practices and their impacts on soil, water, and nutrient dynamics at a landscape scale is an important step in determining and prioritizing areas in a watershed to effectively utilize this practice. However, such data are lacking. Our objective was to develop a spatial and temporal inventory of winter cover cropping practices in the Maumee River watershed using images collected by Landsat satellites (Landsat 5, 7 and 8) from 2008 to 2019 in Google Earth Engine (GEE) platform. Each year, satellite images collected during cover crop growing season (i.e., between October and April) were converted into two seasonal composites based on cover crop phenology. Using these composites, various image-based covariates were extracted for 628 ground-truth (field) data. By integrating ground-truth and image-based covariates, a cover crop classification model based on a random forest (RF) algorithm was developed, trained and validated in GEE platform. Our classification scheme differentiated four cover crop categories: Winter Hardy, Winter Kill, Spring Emergent, and No Cover. The overall classification accuracy was 75%, with a kappa coefficient of 0.63. The results showed that more than 50% of the corn-soybean areas in the Maumee River watershed were without winter crops during 2008–2019 period. It was found that 2019/2020 and 2009/2010 were the years with the largest and lowest cover crop areas, with 34% and 10% in the watershed, respectively. The total cover cropping area was then assessed in relation to fall precipitation and cumulative growing degree days (GDD). There was no apparent increasing trend in cover crop areas between 2008 and 2019, but the variability in cover crops areas was found to be related to higher accumulated GDD and fall precipitation. A detailed understanding of the spatial and temporal distribution of cover crops using GEE could help in promoting site-specific management practices to enhance their environmental benefits. This also has significance to policy makers and funding agencies as they could use the information to localize areas in need of interventions for supporting adoption of cover cropping practice.

Hybrid inversion of radiative transfer models based on high spatial resolution satellite reflectance data improves fractional vegetation cover retrieval in heterogeneous ecological systems after fire

In forest landscapes affected by fire, the estimation of fractional vegetation cover (FVC) from remote sensing data using radiative transfer models (RTMs) enables to evaluate the ecological impact of such disturbance across plant communities at different spatio-temporal scales. Even though, when landscapes are highly heterogeneous, the fine-scale ground spatial variation might not be properly captured if FVC products are provided at moderate or coarse spatial scales, as typical of most of operational Earth observing satellite missions. The objective of this study was to evaluate the potential of a RTM inversion approach for estimating FVC from satellite reflectance data at high spatial resolution as compared to the standard use of coarser imagery. The study was conducted both at landscape and plant community levels within the perimeter of a megafire that occurred in western Mediterranean Basin. We developed a hybrid retrieval scheme based on PROSAIL-D RTM simulations to create a training dataset of top-of-canopy spectral reflectance and the corresponding FVC for the dominant plant communities. The machine learning algorithm Gaussian Processes Regression (GPR) was learned on the training dataset to model the relationship between canopy reflectance and FVC. The GPR model was then applied to retrieve FVC from WorldView-3 (spatial resolution of 2 m) and Sentinel-2 (spatial resolution of 20 m) surface reflectance bands. A set of 75 plots of 2x2m and 45 plots of 20x20m was distributed under a stratified schema across the focal plant communities within the fire perimeter to validate FVC satellite derived retrieval. At landscape scale, the accuracy of the FVC retrieval was substantially higher from WorldView-3 (R² = 0.83; RMSE = 7.92%) than from Sentinel-2 (R² = 0.73; RMSE = 11.89%). At community level, FVC retrieval was more accurate for oak forests than for heathlands and broomlands. The retrieval from WorldView-3 minimized the over- and under-estimation effects at low and high field sampled vegetation cover, respectively. These findings emphasize the effectiveness of high spatial resolution satellite reflectance data to capture FVC ground spatial variability in heterogeneous burned areas using a hybrid RTM retrieval method.

Google Earth Engine as Multi-Sensor Open-Source Tool for Supporting the Preservation of Archaeological Areas: The Case Study of Flood and Fire Mapping in Metaponto, Italy

In recent years, the impact of Climate change, anthropogenic and natural hazards (such as earthquakes, landslides, floods, tsunamis, fires) has dramatically increased and adversely affected modern and past human buildings including outstanding cultural properties and UNESCO heritage sites. Research about protection/monitoring of cultural heritage is crucial to preserve our cultural properties and (with them also) our history and identity. This paper is focused on the use of the open-source Google Earth Engine tool herein used to analyze flood and fire events which affected the area of Metaponto (southern Italy), near the homonymous Greek-Roman archaeological site. The use of the Google Earth Engine has allowed the supervised and unsupervised classification of areas affected by flooding (2013-2020) and fire (2017) in the past years, obtaining remarkable results and useful information for setting up strategies to mitigate damage and support the preservation of areas and landscape rich in cultural and natural heritage.

Exploring the Impact of Noise on Hybrid Inversion of PROSAIL RTM on Sentinel-2 Data

Remote sensing (RS) of biophysical variables plays a vital role in providing the information necessary for understanding spatio-temporal dynamics in ecosystems. The hybrid approach to retrieve biophysical variables from RS by combining Machine Learning (ML) algorithms with surrogate data generated by Radiative Transfer Models (RTM). The susceptibility of the ill-posed solutions to noise currently constrains further application of hybrid approaches. Here, we explored how noise affects the performance of ML algorithms for biophysical trait retrieval. We focused on synthetic Sentinel-2 (S2) data generated using the PROSAIL RTM and four commonly applied ML algorithms: Gaussian Processes (GPR), Random Forests (RFR), and Artificial Neural Networks (ANN) and Multi-task Neural Networks (MTN). After identifying which biophysical variables can be retrieved from S2 using a Global Sensitivity Analysis, we evaluated the performance loss of each algorithm using the Mean Absolute Percentage Error (MAPE) with increasing noise levels. We found that, for S2 data, Carotenoid concentrations are uniquely dependent on band 2, Chlorophyll is almost exclusively dependent on the visible ranges, and Leaf Area Index, water, and dry matter contents are mostly dependent on infrared bands. Without added noise, GPR was the best algorithm (<0.05%), followed by the MTN (<3%) and ANN (<5%), with the RFR performing very poorly (<50%). The addition of noise critically affected the performance of all algorithms (>20%) even at low levels of added noise (≈5%). Overall, both neural networks performed significantly better than GPR and RFR when noise was added with the MTN being slightly better when compared to the ANN. Our results imply that the performance of the commonly used algorithms in hybrid-RTM inversion are pervasively sensitive to noise. The implication is that more advanced models or approaches are necessary to minimize the impact of noise to improve near real-time and accurate RS monitoring of biophysical trait retrieval.

A Survey of Active Learning for Quantifying Vegetation Traits from Terrestrial Earth Observation Data

The current exponential increase of spatiotemporally explicit data streams from satellitebased Earth observation missions offers promising opportunities for global vegetation monitoring. Intelligent sampling through active learning (AL) heuristics provides a pathway for fast inference of essential vegetation variables by means of hybrid retrieval approaches, i.e., machine learning regression algorithms trained by radiative transfer model (RTM) simulations. In this study we summarize AL theory and perform a brief systematic literature survey about AL heuristics used in the context of Earth observation regression problems over terrestrial targets. Across all relevant studies it appeared that: (i) retrieval accuracy of AL-optimized training data sets outperformed models trained over large randomly sampled data sets, and (ii) Euclidean distance-based (EBD) diversity method tends to be the most efficient AL technique in terms of accuracy and computational demand. Additionally, a case study is presented based on experimental data employing both uncertainty and diversity AL criteria. Hereby, a a simulated training data base by the PROSAIL-PRO canopy RTM is used to demonstrate the benefit of AL techniques for the estimation of total leaf carotenoid content (C_xc) and leaf water content (C_w). Gaussian process regression (GPR) was incorporated to minimize and optimize the training data set with AL. Training the GPR algorithm on optimally AL-based sampled data sets led to improved variable retrievals compared to training on full data pools, which is further demonstrated on a mapping example. From these findings we can recommend the use of AL-based sub-sampling procedures to select the most informative samples out of large training data pools. This will not only optimize regression accuracy due to exclusion of redundant information, but also speed up processing time and reduce final model size of kernel-based machine learning regression algorithms, such as GPR. With this study we want to encourage further testing and implementation of AL sampling methods for hybrid retrieval workflows. AL can contribute to the solution of regression problems within the framework of operational vegetation monitoring using satellite imaging spectroscopy data, and may strongly facilitate data processing for cloud-computing platforms.

Monitoring Forest Change in the Amazon Using Multi-Temporal Remote Sensing Data and Machine Learning Classification on Google Earth Engine

Deforestation causes diverse and profound consequences for the environment and species. Direct or indirect effects can be related to climate change, biodiversity loss, soil erosion, floods, landslides, etc. As such a significant process, timely and continuous monitoring of forest dynamics is important, to constantly follow existing policies and develop new mitigation measures. The present work had the aim of mapping and monitoring the forest change from 2000 to 2019 and of simulating the future forest development of a rainforest region located in the Pará state, Brazil. The land cover dynamics were mapped at five-year intervals based on a supervised classification model deployed on the cloud processing platform Google Earth Engine. Besides the benefits of reduced computational time, the service is coupled with a vast data catalogue providing useful access to global products, such as multispectral images of the missions Landsat five, seven, eight and Sentinel-2. The validation procedures were done through photointerpretation of high-resolution panchromatic images obtained from CBERS (China–Brazil Earth Resources Satellite). The more than satisfactory results allowed an estimation of peak deforestation rates for the period 2000–2006; for the period 2006–2015, a significant decrease and stabilization, followed by a slight increase till 2019. Based on the derived trends a forest dynamics was simulated for the period 2019–2028, estimating a decrease in the deforestation rate. These results demonstrate that such a fusion of satellite observations, machine learning, and cloud processing, benefits the analysis of the forest dynamics and can provide useful information for the development of forest policies.

Understanding the Land Surface Phenology and Gross Primary Production of Sugarcane Plantations by Eddy Flux Measurements, MODIS Images, and Data-Driven Models

Sugarcane (complex hybrids of Saccharum spp., C4 plant) croplands provide cane stalk feedstock for sugar and biofuel (ethanol) production. It is critical for us to analyze the phenology and gross primary production (GPP) of sugarcane croplands, which would help us to better understand and monitor the sugarcane growing condition and the carbon cycle. In this study, we combined the data from two sugarcane EC flux tower sites in Brazil and the USA, images from the Moderate Resolution Imaging Spectroradiometer (MODIS) sensor, and data-driven models to study the phenology and GPP of sugarcane croplands. The seasonal dynamics of climate, vegetation indices from MODIS images, and GPP from two sugarcane flux tower sites (GPPEC) reveal the temporal consistency in sugarcane phenology (crop calendar: green-up dates and harvesting dates) as estimated by the vegetation indices and GPPEC data. The Land Surface Water Index (LSWI) is shown to be useful to delineate the phenology of sugarcane croplands. The relationship between the sugarcane GPPEC and the Enhanced Vegetation Index (EVI) is stronger than the relationship between the GPPEC and the Normalized Difference Vegetation Index (NDVI). We ran the Vegetation Photosynthesis Model (VPM), which uses the light use efficiency (LUE) concept and is driven by climate data and MODIS images, to estimate the daily GPP at the two sugarcane sites (GPPVPM). The seasonal dynamics of the GPPVPM and GPPEC at the two sites agreed reasonably well with each other, which indicates that VPM is a powerful tool for estimating the GPP of sugarcane croplands in Brazil and the USA. This study clearly highlights the potential of combining eddy covariance technology, satellite-based remote sensing technology, and data-driven models for better understanding and monitoring the phenology and GPP of sugarcane croplands under different climate and management practices.

Evaluation of Global Decametric-Resolution LAI, FAPAR and FVC Estimates Derived from Sentinel-2 Imagery

Global biophysical products at decametric resolution derived from Sentinel-2 imagery have emerged as a promising dataset for fine-scale ecosystem modeling and agricultural monitoring. Evaluating uncertainties of different Sentinel-2 biophysical products over various regions and vegetation types is pivotal in the application of land surface models. In this study, we quantified the performance of Sentinel-2-derived Leaf Area Index (LAI), Fraction of Absorbed Photosynthetically Active Radiation (FAPAR), and Fractional Vegetation Cover (FVC) estimates using global ground observations with consistent measurement criteria. Our results show that the accuracy of vegetation and non-vegetated classification based on Sentinel-2 surface reflectance products is greater than 95%, which indicates the vegetation identification is favorable for the practical application of biophysical estimates, as several LAI, FAPAR, and FVC retrievals were derived for non-vegetated pixels. The rate of best retrievals is similar between LAI and FAPAR estimates, both accounting for 87% of all vegetation pixels, while it is almost 100% for FVC estimates. Additionally, the Sentinel-2 FAPAR and FVC estimates agree well with ground-measurements-derived (GMD) reference maps, whereas a large discrepancy is observed for Sentinel-2 LAI estimates by comparing with both GMD effective LAI (LAIe) and actual LAI (LAI) reference maps. Furthermore, the uncertainties of Sentinel-2 LAI, FAPAR and FVC estimates are 1.09 m2/m2, 1.14 m2/m2, 0.13 and 0.17 through comparisons to ground LAIe, LAI, FAPAR, and FVC measurements, respectively. Given the temporal difference between Sentinel-2 observations and ground measurements, Sentinel-2 LAI estimates are more consistent with LAIe than LAI values. The robustness of evaluation results can be further improved as long as more multi-temporal ground measurements across different regions are obtained. Overall, this study provides fundamental information about the performance of Sentinel-2 LAI, FAPAR, and FVC estimates, which imbues our confidence in the broad applications of these decametric products.

Generating High Spatio-Temporal Resolution Fractional Vegetation Cover by Fusing GF-1 WFV and MODIS Data

As an important indicator to characterize the surface vegetation, fractional vegetation cover (FVC) with high spatio-temporal resolution is essential for earth surface process simulation. However, due to technical limitations and the influence of weather, it is difficult to generate temporally continuous FVC with high spatio-temporal resolution based on a single remote-sensing data source. Therefore, the objective of this study is to explore the feasibility of generating high spatio-temporal resolution FVC based on the fusion of GaoFen-1 Wide Field View (GF-1 WFV) data and Moderate-resolution Imaging Spectroradiometer (MODIS) data. Two fusion strategies were employed to identify a suitable fusion method: (i) fusing reflectance data from GF-1 WFV and MODIS firstly and then estimating FVC from the reflectance fusion result (strategy FC, Fusion_then_FVC). (ii) fusing the FVC estimated from GF-1 WFV and MODIS reflectance data directly (strategy CF, FVC_then_Fusion). The FVC generated using strategies FC and CF were evaluated based on FVC estimated from the real GF-1 WFV data and the field survey FVC, respectively. The results indicated that strategy CF achieved higher accuracies with less computational cost than those of strategy FC both in the comparisons with FVC estimated from the real GF-1 WFV (CF:R2 = 0.9580, RMSE = 0.0576; FC: R2 = 0.9345, RMSE = 0.0719) and the field survey FVC data (CF: R2 = 0.8138, RMSE = 0.0985; FC: R2 = 0.7173, RMSE = 0.1214). Strategy CF preserved spatial details more accurately than strategy FC and had a lower probability of generating abnormal values. It could be concluded that fusing GF-1 WFV and MODIS data for generating high spatio-temporal resolution FVC with good quality was feasible, and strategy CF was more suitable for generating FVC given its advantages in estimation accuracy and computational efficiency.

Determination of Vegetation Thresholds for Assessing Land Use and Land Use Changes in Cambodia using the Google Earth Engine Cloud-Computing Platform

As more data and technologies become available, it is important that a simple method is developed for the assessment of land use changes because of the global need to understand the potential climate mitigation that could result from a reduction in deforestation and forest degradation in the tropics. Here, we determined the threshold values of vegetation types to classify land use categories in Cambodia through the analysis of phenological behaviors and the development of a robust phenology-based threshold classification (PBTC) method for the mapping and long-term monitoring of land cover changes. We accessed 2199 Landsat collections using Google Earth Engine (GEE) and applied the Enhanced Vegetation Index (EVI) and harmonic regression methods to identify phenological behaviors of land cover categories during the leaf-shedding phenology (LSP) and leaf-flushing phenology (LFS) seasons. We then generated 722 mean phenology EVI profiles for 12 major land cover categories and determined the threshold values for selected land cover categories in the mid-LSP season. The PBTC pixel-based classified map was validated using very high-resolution (VHR) imagery. We obtained a cumulative overall accuracy of more than 88% and a cumulative overall accuracy of the referenced forest cover of almost 85%. These high accuracy values suggest that the very first PBTC map can be useful for estimating the activity data, which are critically needed to assess land use changes and related carbon emissions under the Reducing Emissions from Deforestation and forest Degradation (REDD+) scheme. We found that GEE cloud-computing is an appropriate tool to use to access remote sensing big data at scale and at no cost.

Mapping Winter Crops in China with Multi-Source Satellite Imagery and Phenology-Based Algorithm

Timely and accurate mapping of winter crop planting areas in China is important for food security assessment at a national level. Time-series of vegetation indices, such as the normalized difference vegetation index (NDVI), are widely used for crop mapping, as they can characterize the growth cycle of crops. However, with the moderate spatial resolution optical imagery acquired by Landsat and Sentinel-2, it is difficult to obtain complete time-series curves for vegetation indices due to the influence of the revisit cycle of the satellite and weather conditions. Therefore, in this study, we propose a method for compositing the multi-temporal NDVI, in order to map winter crop planting areas with the Landsat-7 and -8 and Sentinel-2 optical images. The algorithm composites the multi-temporal NDVI into three key values, according to two time-windows—a period of low NDVI values and a period of high NDVI values—for the winter crops. First, we identify the two time-windows, according to the time-series of the NDVI obtained from daily Moderate Resolution Imaging Spectroradiometer observations. Second, the 30 m spatial resolution multi-temporal NDVI curve, derived from the Landsat-7 and -8 and Sentinel-2 optical images, is composited by selecting the maximal value in the high NDVI value period, and the minimal and median values in the low NDVI value period, using an algorithm of the Google Earth Engine. Third, a decision tree classification method is utilized to perform the winter crop classification at a pixel level. The results indicate that this method is effective for the large-scale mapping of winter crops. In the study area, the area of winter crops in 2018 was determined to be 207,641 km2, with an overall accuracy of 96.22% and a kappa coefficient of 0.93. The method proposed in this paper is expected to contribute to the rapid and accurate mapping of winter crops in large-scale applications and analyses.

Google Earth Engine Applications

The Google Earth Engine (GEE) is a cloud computing platform designed to store and process huge data sets (at petabyte-scale) for analysis and ultimate decision making [...]