Improving predictions of evapotranspiration by integrating multi-source observations and land surface model

He, Xinlei; Liu, Shaomin; Xu, Tong; Yu, Kailiang; Gentine, Pierre; Zhang, Zhe; Xu, Ziwei; Jiao, Dandan; Wu, Dongxing

doi:10.1016/j.agwat.2022.107827

Cited by 17 publications

(15 citation statements)

References 121 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…In this study, the hybrid model proposed by He et al (2022) based on the DA and ML methods was incorporated into the WRF model to improve the LAI, SM, and ET simulations. The hybrid approach relies on the DA method to update the vegetation dynamics of the Noah-MP model and the ML method to construct a three-layer SM surrogate model.…”

Section: Hybrid Modelmentioning

confidence: 99%

“…Although land surface models (LSMs) have been improved incrementally in the past decades, it is still challenging to effectively couple LSMs with atmospheric models to improve the description of land-atmosphere interactions (Chen and Dudhia, 2001;Liu et al, 2021). The success of the coupling depends not only on the sophisticated physical processes of the LSMs, but also on soil and vegetation characteristics and the accurate characterization of the water vapor fluxes at the land-atmosphere interface (Gentine et al, 2019;Zhang et al, 2021bZhang et al, , 2022.…”

Section: Introductionmentioning

confidence: 99%

“…Thus, ML-based approaches can create beneficial pathways for knowledge discovery in process models based on extensible data (Moosavi et al, 2021;Reichstein et al, 2019). The main improvements are focused on model approximation, parameterization, bias correction, and hybrid modeling (Brajard et al, 2020;He et al, 2022;Jia et al, 2021;Xu et al, 2014;Zhao et al, 2019). Several studies https://doi.org/10.5194/hess-2022-379 Preprint.…”

Section: Introductionmentioning

confidence: 99%

“…have shown that the integration of the DA and ML methods can enhance the reliability of predictions and reduce simulation errors by including physical information in observed data (Brajard et al, 2020;Buizza et al, 2022;Forman and Xue, 2017;Gottwald and Reich, 2021;He et al, 2022). Forman and Xue (2017) integrated a ML model (as a measurement operator) into a DA system to improve the estimation of snow water equivalent.…”

Section: Introductionmentioning

confidence: 99%

“…Zhao et al (2019) used a physics-constrained ML method to improve the latent heat fluxes estimates. He et al (2022) proposed a hybrid model that can integrate remotely sensed LAI and multi-source SM observations to improve the estimation of ET within the coupled DA and ML framework.…”

Section: Introductionmentioning

confidence: 99%

See 4 more Smart Citations

Improving predictions of land-atmosphere interactions based on a hybrid data assimilation and machine learning method

Liu

et al. 2022

Preprint

View full text Add to dashboard Cite

Abstract. The energy and moisture exchange between the land surface and atmospheric boundary layer plays a critical role in regional climate simulations. This paper implemented a hybrid data assimilation and machine learning framework (DA-ML method) into the Weather Research and Forecasting (WRF) model to optimize surface soil and vegetation conditions. The hybrid method can integrate remotely sensed leaf area index (LAI), multi-source soil moisture (SM) observations, and land surface models (LSMs) to accurately describe land surface states and fluxes. The performance of the hybrid method on the regional climate was evaluated in the Heihe River Basin (HRB), the second largest endorheic river basin in Northwest China. The findings indicate that the DA-ML method improved the estimation of evapotranspiration (ET) and generated a spatial distribution consistent with the ML-based watershed ET (ETMap). The WRF simulations overestimated (underestimated) the air temperature (specific humidity) in the vegetated areas of the HRB. In contrast, the estimated air temperature and specific humidity from WRF (DA-ML) agree well with the observations, especially in the midstream oasis. The DA-ML framework enhanced oasis-desert interactions by improving the soil and vegetation characteristics. The wetting and cooling effects and wind shield effects of the oasis were enhanced by the DA-ML. The wetting and cooling effect of the oasis can transfer water vapor to the surrounding desert, which benefits the oasis-desert ecosystem. The results show that the wetting and cooling effects only negligibly changed the local precipitation in the midstream oasis. However, upstream of the HRB, the integration of LAI and SM will induce water vapor intensification and promote precipitation, particularly on windward slopes.

show abstract

Section: Hybrid Modelmentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

See 3 more Smart Citations

Improving predictions of land-atmosphere interactions based on a hybrid data assimilation and machine learning method

Liu

et al. 2022

Preprint

View full text Add to dashboard Cite

show abstract

Estimation of water balance components by Noah-MP land surface model for the Neyshaboor watershed, Khorasan Razavi, Iran

Mirshafee,

Ansari,

Davary

et al. 2024

Appl Water Sci

View full text Add to dashboard Cite

The numerical modeling of the land surface can make up for the insufficient station data in terms of number, dispersion, and temporal continuity. In this research, to evaluate the Noah-MP land surface model, the water balance components were estimated in the Neyshaboor watershed in the monthly time step during 2000–2009. Model input data were obtained from the global land data assimilation system version 1 (GLDAS-1), and the SWAT (soil and water assessment tool, a semi-distributed for small watershed to river basin-scale model) model output was used for the evaluation of the Noah-MP model. In this study, the ability of the Noah-MP model in simulating vegetation dynamically was studied. The precipitation was corrected before running the model for a more reliable evaluation. The time between 2000 and 2001 was considered a spin-up period and 2002–2009 for calibration and validation. The model has the best simulation in the mountainous areas; the runoff simulated by the Noah-MP model is in good agreement with the modeled runoff by SWAT in these areas. (R2 = 0.78, NSE = 0.62, RMSE = 1.98 m3/s). The R2 for simulated soil moisture for soil layers (0–10, 10–40 cm) was 0.62 and 0.57, and RMSE was 0.059 (m3/m3) and 0.052 (m3/m3), respectively, in Motamedieh field. The annual amount of evapotranspiration estimated by the two models is comparable to the average annual evapotranspiration in the watershed (about 300 mm). Based on the results from the research, the model has well simulated: the runoff in the mountainous areas, the moisture in the upper layer of the soil, and the average annual evapotranspiration in the study area.

show abstract

Evaluation of the intrinsic temperature sensitivity of ecosystem respiration in typical ecosystems of an endorheic river basin

Liu

et al. 2023

Agricultural and Forest Meteorology

View full text Add to dashboard Cite

Improving predictions of evapotranspiration by integrating multi-source observations and land surface model

Cited by 17 publications

References 121 publications

Improving predictions of land-atmosphere interactions based on a hybrid data assimilation and machine learning method

Improving predictions of land-atmosphere interactions based on a hybrid data assimilation and machine learning method

Estimation of water balance components by Noah-MP land surface model for the Neyshaboor watershed, Khorasan Razavi, Iran

Evaluation of the intrinsic temperature sensitivity of ecosystem respiration in typical ecosystems of an endorheic river basin

Contact Info

Product

Resources

About