Reconstruction of high spatial resolution surface air temperature data across China: A new geo-intelligent multisource data-based machine learning technique

Zhu, Xiudi; Zhang, Qiang; Xu, Chong‐Yu; Sun, Peng; Pan, Hongbin

doi:10.1016/j.scitotenv.2019.02.077

Cited by 37 publications

(23 citation statements)

References 65 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Machine learning has shown remarkable potential in geosciences in recent years for various applications such as land use change detection, precipitation prediction and bias-correcting forecast [17][18][19]. Deep learning methods have made revolutionary advances in the sequential data-modeling domain [20][21][22][23][24] or for streamflow forecasting [25]. Recently, several studies have used the so-called hybrid modeling approach, coupling physical-models with machine learning [20,21,26].…”

Section: Introductionmentioning

confidence: 99%

Evaluation and machine learning improvement of global hydrological model-based flood simulations

Tao

Sun

Gentine

et al. 2019

Environ. Res. Lett.

118

View full text Add to dashboard Cite

A warmer climate is expected to accelerate global hydrological cycle, causing more intense precipitation and floods. Despite recent progress in global flood risk assessment, the accuracy and improvement of global hydrological models (GHMs)-based flood simulation is insufficient for most applications. Here we compared flood simulations from five GHMs under the Inter-Sectoral Impact Model Intercomparison Project 2a (ISIMIP2a) protocol, against those calculated from 1032 gauging stations in the Global Streamflow Indices and Metadata Archive for the historical period 1971-2010. A machine learning approach, namely the long short-term memory units (LSTM) was adopted to improve the GHMs-based flood simulations within a hybrid physics-machine learning approach (using basin-averaged daily mean air temperature, precipitation, wind speed and the simulated daily discharge from GHMs-CaMa-Flood model chain as the inputs of LSTM, and observed daily discharge as the output value). We found that the GHMs perform reasonably well in terms of amplitude of peak discharge but are relatively poor in terms of their timing. The performance indicated great discrepancy under different climate zones. The large difference in performance between GHMs and observations reflected that those simulations require improvements. The LSTM used in combination with those GHMs was then shown to drastically improve the performance of global flood simulations (especially in terms of amplitude of peak discharge), suggesting that the combination of classical flood simulation and machine learning techniques might be a way forward for more robust and confident flood risk assessment.

show abstract

Section: Introductionmentioning

confidence: 99%

Evaluation and machine learning improvement of global hydrological model-based flood simulations

Tao

Sun

Gentine

et al. 2019

Environ. Res. Lett.

118

View full text Add to dashboard Cite

show abstract

“…Instead, we just directly add geo-coordinates (longitude and latitude) and time information (day of the year) into the feature space as that done in other studies (e.g. [52] [53] [54] [55] [56] [57] [58]). In total, we selected 11 variables as the candidate features based on our domain knowledge.…”

Section: Feature Selectionmentioning

confidence: 99%

Aerosol Absorption Over Land Derived From the Ultra-Violet Aerosol Index by Deep Learning

Sun¹,

Veefkind²,

Velthoven³

et al. 2021

IEEE J. Sel. Top. Appl. Earth Observations Remote Sensing

View full text Add to dashboard Cite

Quantitative measurements of aerosol absorptive properties, e.g. the absorbing aerosol optical depth (AAOD) and the single scattering albedo (SSA), are important to reduce uncertainties of aerosol climate radiative forcing assessments. Currently, global retrievals of AAOD and SSA are mainly provided by the ground-based Aerosol RObotic NETwork (AERONET), whereas it is still challenging to retrieve them from space. However, we found the AERONET AAOD has a relatively strong correlation with the satellite retrieved Ultra-Violet Aerosol Index (UVAI). Based on this, a numerical relation is built by a Deep Neural Network (DNN) to predict global AAOD and SSA over land from the long-term UVAI record (2006 to 2019) provided by the Ozone Monitoring Instrument (OMI) onboard Aura. The DNN predicted aerosol absorption is satisfying for samples with AOD at 550 nm larger than 0.1, and the DNN model performance is better for smaller absorbing aerosols (e.g. smoke) than larger ones (e.g. mineral dust). The comparison of the DNN predictions with AERONET shows a high correlation coefficient of 0.90 and a root mean square of 0.005 for the AAOD, and over 80% of samples are within the expected uncertainty of AERONET SSA (±0.03).

show abstract

“…The authors showed that adding these covariates improved prediction and produced results that mimic kriging. Zhu et al [25] proposed an ML model which considers autocorrelation to reconstruct surface air temperature data at high spatial resolution across China. They added weights based on altitude and distance differences between the target station and surrounding stations as covariates.…”

Section: Introductionmentioning

confidence: 99%

Random Forest Spatial Interpolation

et al. 2020

View full text Add to dashboard Cite

For many decades, kriging and deterministic interpolation techniques, such as inverse distance weighting and nearest neighbour interpolation, have been the most popular spatial interpolation techniques. Kriging with external drift and regression kriging have become basic techniques that benefit both from spatial autocorrelation and covariate information. More recently, machine learning techniques, such as random forest and gradient boosting, have become increasingly popular and are now often used for spatial interpolation. Some attempts have been made to explicitly take the spatial component into account in machine learning, but so far, none of these approaches have taken the natural route of incorporating the nearest observations and their distances to the prediction location as covariates. In this research, we explored the value of including observations at the nearest locations and their distances from the prediction location by introducing Random Forest Spatial Interpolation (RFSI). We compared RFSI with deterministic interpolation methods, ordinary kriging, regression kriging, Random Forest and Random Forest for spatial prediction (RFsp) in three case studies. The first case study made use of synthetic data, i.e., simulations from normally distributed stationary random fields with a known semivariogram, for which ordinary kriging is known to be optimal. The second and third case studies evaluated the performance of the various interpolation methods using daily precipitation data for the 2016–2018 period in Catalonia, Spain, and mean daily temperature for the year 2008 in Croatia. Results of the synthetic case study showed that RFSI outperformed most simple deterministic interpolation techniques and had similar performance as inverse distance weighting and RFsp. As expected, kriging was the most accurate technique in the synthetic case study. In the precipitation and temperature case studies, RFSI mostly outperformed regression kriging, inverse distance weighting, random forest, and RFsp. Moreover, RFSI was substantially faster than RFsp, particularly when the training dataset was large and high-resolution prediction maps were made.

show abstract

Reconstruction of high spatial resolution surface air temperature data across China: A new geo-intelligent multisource data-based machine learning technique

Cited by 37 publications

References 65 publications

Evaluation and machine learning improvement of global hydrological model-based flood simulations

Evaluation and machine learning improvement of global hydrological model-based flood simulations

Aerosol Absorption Over Land Derived From the Ultra-Violet Aerosol Index by Deep Learning

Random Forest Spatial Interpolation

Contact Info

Product

Resources

About