Optical vegetation indices for monitoring terrestrial ecosystems globally

Zeng, Yelu; Hao, Dalei; Huete, Alfredo; Dechant, Benjamin; Berry, J. A.; Chen, Jing M.; Joiner, Joanna; Frankenberg, Christian; Bond‐Lamberty, Ben; Ryu, Youngryel; Xiao, Jingfeng; Asrar, Ghassem; Chen, Min

doi:10.1038/s43017-022-00298-5

Cited by 344 publications

(154 citation statements)

References 175 publications

Supporting

Mentioning

149

Contrasting

Unclassified

Order By: Relevance

“…Accuracy metric used: R-squared (in the validation phase) lowest average accuracy was found for shrub sites, which may be related to the difficulty of the remote-sensing-based vegetation index (e.g., NDVI) to quantify the physiological and ecological conditions of shrubs (Zeng et al, 2022), and the heterogeneity of the spatial distribution of shrubs within the EC observation area may also cause difficulties in capturing their relationships with biophysical variables. We also found high model accuracy for the wetland type, although records as evidence to support this finding may be limited.…”

Section: Accuracy Metricmentioning

confidence: 99%

“…However, due to the high proportion of models with small temporal scales (e.g., halfhourly scale, hourly scale, and daily scale) in this study, this advantage of the combination of meteorological variables may be more suitable for small temporal scales. A possible explanation is that vegetation-related variables such as NDVI and LAI at the daily scale, 8 d scale, and 16 d scale have limited explanatory ability for hourly or daily-scale variability in ET, especially under cloudy conditions (e.g., tropical rainforest regions); the temporal continuity of the vegetation index data may be greatly limited (Zeng et al, 2022). This should be given more attention, and some vegetation indices derived from hourly temporal resolution satellite remote-sensing data such as GOES (Zeng et al, 2022) can be used for ET simulations to investigate the possible added value of vegetation indices at smaller timescales.…”

Section: Comprehensive Insights On Model Featuresmentioning

confidence: 99%

“…A possible explanation is that vegetation-related variables such as NDVI and LAI at the daily scale, 8 d scale, and 16 d scale have limited explanatory ability for hourly or daily-scale variability in ET, especially under cloudy conditions (e.g., tropical rainforest regions); the temporal continuity of the vegetation index data may be greatly limited (Zeng et al, 2022). This should be given more attention, and some vegetation indices derived from hourly temporal resolution satellite remote-sensing data such as GOES (Zeng et al, 2022) can be used for ET simulations to investigate the possible added value of vegetation indices at smaller timescales. In contrast, at a small temporal scale, the use of combinations of meteorological variables can capture moisture and energy conditions that control the rapid fluctuations of ET and thus has a dominant role in hourly or daily-scale ET prediction.…”

Section: Comprehensive Insights On Model Featuresmentioning

confidence: 99%

“…For the use of various predictor combinations with "&", the value for "used together " is set as 1, and other conditions are set as 0 (e.g., for the There are differences in model accuracy among different PFTs. For example, in forest sites, limitations in data accuracy of factors were possible because some remote-sensingbased predictors such as NDVI, FAPAR, and LAI have limited accuracy when applied to forest types (Liu et al, 2018b;Zeng et al, 2022). In addition, factors such as crown density, which may significantly affect the proportion of soil evaporation, transpiration, and evaporation of canopy interception, were not considered in these models, which may also lead to low model accuracy.…”

Section: Comprehensive Insights On Model Featuresmentioning

confidence: 99%

See 3 more Smart Citations

Evaluation of water flux predictive models developed using eddy-covariance observations and machine learning: a meta-analysis

Shi

Luo

Hellwich

et al. 2022

Hydrol. Earth Syst. Sci.

View full text Add to dashboard Cite

With the rapid accumulation of water flux observations from global eddy-covariance flux sites, many studies have used data-driven approaches to model water fluxes, with various predictors and machine learning algorithms used. However, it is unclear how various model features affect prediction accuracy. To fill this gap, we evaluated this issue based on records of 139 developed models collected from 32 such studies. Support vector machines (SVMs; average R-squared = 0.82) and RF (random forest; average R-squared = 0.81) outperformed other evaluated algorithms with sufficient sample size in both cross-study and intrastudy (with the same data) comparisons. The average accuracy of the model applied to arid regions is higher than in other climate types. The average accuracy of the model was slightly lower for forest sites (average R-squared = 0.76) than for croplands and grasslands (average R-squared = 0.8 and 0.79) but higher than for shrubland sites (average Rsquared = 0.67). Using R n /R s , precipitation, T a , and the fraction of absorbed photosynthetically active radiation (FA-PAR) improved the model accuracy. The combined use of T a and R n /R s is very effective, especially in forests, while in grasslands the combination of W s and R n /R s is also effective. Random cross-validation showed higher model accuracy than spatial cross-validation and temporal crossvalidation, but spatial cross-validation is more important in spatial extrapolation. The findings of this study are promising to guide future research on such machine-learning-based modeling. IntroductionEvapotranspiration (ET) is one of the most important components of the water cycle in terrestrial ecosystems. It also represents the key variable in linking ecosystem functioning, carbon and climate feedback, agricultural management, and water resources (Fisher et al., 2017). The quantification of ET for regions, continents, or the globe can improve our understanding of water, heat, and carbon interactions, which is important for global change research (Xu et al., 2018). Information on ET has been used in many fields, including, but not limited to, droughts and heat waves (Miralles et al., 2014), regional water balance closures (Chen et al., 2014;Sahoo et al., 2011), agricultural management (Allen et al., 2011, water resources management (Anderson et al., 2012),

show abstract

Section: Accuracy Metricmentioning

confidence: 99%

Section: Comprehensive Insights On Model Featuresmentioning

confidence: 99%

Section: Comprehensive Insights On Model Featuresmentioning

confidence: 99%

Section: Comprehensive Insights On Model Featuresmentioning

confidence: 99%

See 2 more Smart Citations

Evaluation of water flux predictive models developed using eddy-covariance observations and machine learning: a meta-analysis

Shi

Luo

Hellwich

et al. 2022

Hydrol. Earth Syst. Sci.

View full text Add to dashboard Cite

show abstract

“…In the age of satellites, "big data", and a growing trend of opening access to information, more scholars hope to directly quantify land use change, which is critical to addressing global societal challenges such as food security, climate change, and biodiversity loss [3]. Most of the quantification of land use change is carried out by means of satellite remote sensing, inventory, statistical data, etc., among which remote sensing satellites refer to land cover (the biophysical properties of a land surface, e.g., grassland), provide high spatial resolution, and are an effective means to detect large-scale, long-term land use changes [32]. Research has showed that global land use changes are four times greater than previously estimated [3], especially in Southeastern Asia.…”

Section: Introductionmentioning

confidence: 99%

Revealing the Land Use Volatility Process in Northern Southeast Asia

Rao

Zhang

2022

Land

View full text Add to dashboard Cite

Frequent land use change has generally been considered as a consequence of human activities. Here, we revealed the land use volatility process in northern Southeast Asia (including parts of Myanmar, Thailand, Laos, Vietnam, and China) from 2000 to 2018 with LandTrendr in the Google Earth Engine (GEE) platform based on the Normalized Burning Index (NBR). The result showed that land use volatility with similar degrees had very obvious aggregation characteristics in time and space in the study area, and the time for the occurrence of land use volatility in adjacent areas was often relatively close. This trend will become more obvious with the intensity of land use volatility. At the same time, land use volatility also has obvious spillover effects, and strong land use volatility will drive changes in the surrounding land. If combined with the land use/cover types, which are closely related to human activities that could have more severe land use volatility, and with the increase of the volatility intensity, the proportion of the land use type with strong land use volatility will gradually increase. Revealing the land use volatility process has a possibility to deepen the understanding of land use change and to help formulate land use policy.

show abstract

Integrating forest structural diversity measurement into ecological research

Atkins,

Bhatt,

Carrasco

et al. 2023

Ecosphere

View full text Add to dashboard Cite

The measurement of forest structure has evolved steadily due to advances in technology, methodology, and theory. Such advances have greatly increased our capacity to describe key forest structural elements and resulted in a range of measurement approaches from traditional analog tools such as measurement tapes to highly derived and computationally intensive methods such as advanced remote sensing tools (e.g., lidar, radar). This assortment of measurement approaches results in structural metrics unique to each method, with the caveat that metrics may be biased or constrained by the measurement approach taken. While forest structural diversity (FSD) metrics foster novel research opportunities, understanding how they are measured or derived, limitations of the measurement approach taken, as well as their biological interpretation is crucial for proper application. We review the measurement of forest structure and structural diversity—an umbrella term that includes quantification of the distribution of functional and biotic components of forests. We consider how and where these approaches can be used, the role of technology in measuring structure, how measurement impacts extend beyond research, and current limitations and potential opportunities for future research.

show abstract

Optical vegetation indices for monitoring terrestrial ecosystems globally

Cited by 344 publications

References 175 publications

Evaluation of water flux predictive models developed using eddy-covariance observations and machine learning: a meta-analysis

Evaluation of water flux predictive models developed using eddy-covariance observations and machine learning: a meta-analysis

Revealing the Land Use Volatility Process in Northern Southeast Asia

Integrating forest structural diversity measurement into ecological research

Contact Info

Product

Resources

About