Short-Term Soil Moisture Forecasting via Gaussian Process Regression with Sample Selection

Mingshuai Liu; Chao Huang; Long Wang; Yu Zhang; Xiong Luo

doi:10.3390/w12113085

Short-Term Soil Moisture Forecasting via Gaussian Process Regression with Sample Selection

Mingshuai Liu, Chao Huang, Long Wang^*, Yu Zhang, Xiong Luo

^*Corresponding author for this work

Research output: Journal Publications and Reviews › RGC 21 - Publication in refereed journal › peer-review

33 Citations (Scopus)

61 Downloads (CityUHK Scholars)

Abstract

Soil moisture is a critical limiting factor for crop growth. Accurate soil moisture prediction helps to schedule irrigation and improve the crop production. A soil moisture prediction method based on Gaussian Process Regression (GPR) is proposed in this paper. In order to reduce the computation time of the GPR model, the Radially Uniform (RU) design algorithm was incorporated into the sample selection during the training procedure. Thus, representative training samples are identified and less training time is required. To validate the proposed prediction model, the soil moisture data collected in Beijing, China, was fully utilized. The experimental results demonstrate that the forecasting performance of the GPR model with the RU design algorithm is generally better than that of the generic GPR model in terms of less forecasting errors for both deterministic and probabilistic forecasting, while less computing time is needed for the model training.

Original language	English
Article number	3085
Number of pages	17
Journal	Water (Switzerland)
Volume	12
Issue number	11
Online published	3 Nov 2020
DOIs	https://doi.org/10.3390/w12113085
Publication status	Published - Nov 2020
Externally published	Yes

Funding

Funding: This work was supported in part by the National Key R&D Program of China under Grant 2018YFC0810600, in part by Scientific and Technological Innovation Foundation of Shunde Graduate School, USTB under Grants BK19BF006 and BK20BF010, in part by the Interdisciplinary Research Project for Young Teachers of USTB (Fundamental Research Funds for the Central Universities) under Grant FRF-IDRY-19-017, in part by the Fundamental Research Funds for the Central Universities under Grants 06500078 and 06500103, in part by the Beijing Natural Science Foundation under Grant 9204028, in part by the Beijing Talents Plan under Grant BJSQ2020008, in part by the Visiting Scholarship of State Key Laboratory of Power Transmission Equipment & System Security and New Technology (Chongqing University), and in part by the Open Research Subject of Key Laboratory of Fluid and Power Machinery (Xihua University), Ministry of Education, under Grant szjj2019-011.

Research Keywords

Gaussian Process Regression
Radially Uniform design
Soil moisture forecasting

Publisher's Copyright Statement

This full text is made available under CC-BY 4.0. https://creativecommons.org/licenses/by/4.0/

Access Output

10.3390/w12113085

123533656.pdfFinal Published version, 3.27 MBLicence: CC BY

Other Access Options

Check CityUHK Library

Permanent Link

Right click to copy link

Cite this

@article{a9b1582080dd41cd90e6690646f36638,

title = "Short-Term Soil Moisture Forecasting via Gaussian Process Regression with Sample Selection",

abstract = "Soil moisture is a critical limiting factor for crop growth. Accurate soil moisture prediction helps to schedule irrigation and improve the crop production. A soil moisture prediction method based on Gaussian Process Regression (GPR) is proposed in this paper. In order to reduce the computation time of the GPR model, the Radially Uniform (RU) design algorithm was incorporated into the sample selection during the training procedure. Thus, representative training samples are identified and less training time is required. To validate the proposed prediction model, the soil moisture data collected in Beijing, China, was fully utilized. The experimental results demonstrate that the forecasting performance of the GPR model with the RU design algorithm is generally better than that of the generic GPR model in terms of less forecasting errors for both deterministic and probabilistic forecasting, while less computing time is needed for the model training.",

keywords = "Gaussian Process Regression, Radially Uniform design, Soil moisture forecasting",

author = "Mingshuai Liu and Chao Huang and Long Wang and Yu Zhang and Xiong Luo",

note = "Publisher Copyright: {\textcopyright} 2020 by the authors. Licensee MDPI, Basel, Switzerland.",

year = "2020",

month = nov,

doi = "10.3390/w12113085",

language = "English",

volume = "12",

journal = "Water (Switzerland)",

issn = "2073-4441",

publisher = "Multidisciplinary Digital Publishing Institute (MDPI)",

number = "11",

}

TY - JOUR

T1 - Short-Term Soil Moisture Forecasting via Gaussian Process Regression with Sample Selection

AU - Liu, Mingshuai

AU - Huang, Chao

AU - Wang, Long

AU - Zhang, Yu

AU - Luo, Xiong

PY - 2020/11

Y1 - 2020/11

N2 - Soil moisture is a critical limiting factor for crop growth. Accurate soil moisture prediction helps to schedule irrigation and improve the crop production. A soil moisture prediction method based on Gaussian Process Regression (GPR) is proposed in this paper. In order to reduce the computation time of the GPR model, the Radially Uniform (RU) design algorithm was incorporated into the sample selection during the training procedure. Thus, representative training samples are identified and less training time is required. To validate the proposed prediction model, the soil moisture data collected in Beijing, China, was fully utilized. The experimental results demonstrate that the forecasting performance of the GPR model with the RU design algorithm is generally better than that of the generic GPR model in terms of less forecasting errors for both deterministic and probabilistic forecasting, while less computing time is needed for the model training.

AB - Soil moisture is a critical limiting factor for crop growth. Accurate soil moisture prediction helps to schedule irrigation and improve the crop production. A soil moisture prediction method based on Gaussian Process Regression (GPR) is proposed in this paper. In order to reduce the computation time of the GPR model, the Radially Uniform (RU) design algorithm was incorporated into the sample selection during the training procedure. Thus, representative training samples are identified and less training time is required. To validate the proposed prediction model, the soil moisture data collected in Beijing, China, was fully utilized. The experimental results demonstrate that the forecasting performance of the GPR model with the RU design algorithm is generally better than that of the generic GPR model in terms of less forecasting errors for both deterministic and probabilistic forecasting, while less computing time is needed for the model training.

KW - Gaussian Process Regression

KW - Radially Uniform design

KW - Soil moisture forecasting

UR - http://www.scopus.com/inward/record.url?scp=85095931774&partnerID=8YFLogxK

UR - https://www.scopus.com/record/pubmetrics.uri?eid=2-s2.0- 85095931774&origin=recordpage

U2 - 10.3390/w12113085

DO - 10.3390/w12113085

M3 - RGC 21 - Publication in refereed journal

AN - SCOPUS:85095931774

SN - 2073-4441

VL - 12

JO - Water (Switzerland)

JF - Water (Switzerland)

IS - 11

M1 - 3085

ER -

Short-Term Soil Moisture Forecasting via Gaussian Process Regression with Sample Selection

Abstract

Funding

Research Keywords

Publisher's Copyright Statement

Access Output

Other Access Options

Permanent Link

Other Files and Links

Fingerprint

Cite this