Data Mining Approach to Predicting Soil Moisture Based on Meteorological Factors and Flow Rates

Su Hoon Choi; Sang-Hyun Lee; Ung Yang; Min Soo Kim

doi:10.7235/HORT.20240001

All Issue

2024 Vol.42, Issue 1 Next Page

Research Article

Data Mining Approach to Predicting Soil Moisture Based on Meteorological Factors and Flow Rates

28 February 2024. pp. 1-14

PDF XML

Abstract

Accurate predictions of the soil moisture, a major limitation related to crop growth, are essential for effective irrigation planning, yield predictions, and proper water resource management. Current attempts to predict soil moisture levels have relied on historical soil moisture data; however, obtaining this type of data can be challenging for farmers engaged in outdoor cultivation. Therefore, this study aimed to predict current soil moisture contents based only on meteorological and flow rate data without previous soil moisture information. To predict the soil moisture, data mining approaches, in this case random forest (RF), support vector regression (SVR), and deep neural network (DNN), were employed. Through the Granger causality test, explanatory variables were determined at different time lags extending to three hours as model inputs for soil moisture predictions. The predictive performance of the models was found to be improved when all meteorological and flow rate data ranging from the previous to the current time could be used as opposed to only data from the current time. The results obtained for the test set showed that the best performance was achieved by the DNN model when it applied explanatory variables from “t” to “t-3” time points with a RMSE of 1.542 and a R2 value of 0.580. These results can enable real-time soil moisture data monitoring for farmers who currently lack access to soil databases. The constructed model is expected to serve as a framework for future studies that consider various environmental factors, such as soil characteristics, topography, and vegetation patterns.

Keywords

deep neural network

granger causality test

random forest

support vector regression

time lags

References

Acharya U, Daigh AL, Oduor PG (2021) Machine learning for predicting field soil moisture using soil, crop, and nearby weather station data in the Red River Valley of the North. Soil Syst 5:57. doi:10.1016/S0022-1694(02)00016-1 10.1016/S0022-1694(02)00016-1

Adeyemi O, Grove I, Peets S, Domun Y, Norton T (2018) Dynamic neural network modelling of soil moisture content for predictive irrigation scheduling. Sens 18:3408. doi:10.3390/s18103408 10.3390/s1810340830314346PMC6210977

Aerts R (1997) Climate, leaf litter chemistry and leaf litter decomposition in terrestrial ecosystems: a triangular relationship. Oikos 79:439-449. doi:10.2307/3546886 10.2307/3546886

Breiman L (1996) Bagging predictors. Mach Learn 24:123-140. doi:10.1007/BF00058655 10.1007/BF00058655

Breiman L (2001) Random forests. Mach Learn 45:5-32. doi:10.1023/A:1010933404324 10.1023/A:1010933404324

Bressler SL, Seth AK (2011) Wiener-Granger causality: a well established methodology. Neuroimage 58:323-329. doi:10.1016/j.neuroimage.2010.02.059 10.1016/j.neuroimage.2010.02.05920202481

Cai Y, Zheng W, Zhang X, Zhangzhong L, Xue X (2019) Research on soil moisture prediction model based on deep learning. PLoS ONE 14:e0214508. doi:10.1371/journal.pone.0214508 10.1371/journal.pone.021450830943228PMC6447191

Cortes C, Vapnik V (1995) Support-vector networks. Mach Learn 20:273-297. doi:10.1007/BF00994018 10.1007/BF00994018

Cutler A, Cutler DR, Stevens JR (2012) Random Forests. In C Zhang, Y Ma, eds, Ensemble machine learning. Springer, New York, NY, pp 157-175. doi:10.1007/978-1-4419-9326-7_5 10.1007/978-1-4419-9326-7_5

Deutsch ES, Bork EW, Willms WD (2010) Soil moisture and plant growth responses to litter and defoliation impacts in Park-land grasslands. Agric Ecosyst Environ 135:1-9. doi:10.1016/j.agee.2009.08.002 10.1016/j.agee.2009.08.002

Dickey DA, Fuller WA (1979) Distribution of the estimators for autoregressive time series with a unit root. J Am Stat Assoc 74:427-431. doi:10.1080/01621459.1979.10482531 10.1080/01621459.1979.10482531

Dirmeyer PA, Schlosser CA, Brubaker KL (2009) Precipitation, recycling, and land memory: An integrated analysis. J Hydrometeorol 10:278-288. doi:10.1175/2008JHM1016.1 10.1175/2008JHM1016.1

Filipović N, Brdar S, Mimić G, Marko O, Crnojević V (2022) Regional soil moisture prediction system based on Long Short-Term Memory network. Biosyst Eng 213:30-38. doi:10.1016/j.biosystemseng.2021.11.019 10.1016/j.biosystemseng.2021.11.019

Gao P, Qiu H, Lan Y, Wang W, Chen W, Han X, Lu J (2022) Modeling for the prediction of soil moisture in litchi orchard with deep long short-term memory. Agriculture 12:25. doi:10.3390/agriculture12010025 10.3390/agriculture12010025

Garcia GM, Pachepsky YA, Vereecken H (2014) Effect of soil hydraulic properties on the relationship between the spatial mean and variability of soil moisture. J Hydrol 516:154-160. doi:10.1016/j.jhydrol.2014.01.069 10.1016/j.jhydrol.2014.01.069

Gill MK, Asefa T, Kemblowski MW, McKee M (2006) Soil moisture prediction using support vector machines. J Am Water Resour Assoc 42:1033-1046. doi:10.1111/j.1752-1688.2006.tb04512.x 10.1111/j.1752-1688.2006.tb04512.x

Gomathi R, Gururaja Rao PN, Chandran K, Selvi A (2015) Adaptive responses of sugarcane to waterlogging stress: An over view. Sugar Tech 17:325-338. doi:10.1007/s12355-014-0319-0 10.1007/s12355-014-0319-0

Granger CW (1969) Investigating causal relations by econometric models and cross-spectral methods. J Econom 424-438. doi:10.2307/1912791 10.2307/1912791

Grayson RB, Western AW, Blöschl G (1997) Preferred states in spatial soil moisture patterns: local and non local controls. Water Resour Res 33:2897-2908. doi:10.1029/97WR02174 10.1029/97WR02174

Hou XL, Feng YH, Wu GH, He YX, Chang DM, Yang H (2016) Application research on artificial neural network dynamic prediction model of soil moisture. Water Saving Irrig 7:70-72

Hupet F, Vanclooster M (2002) Intraseasonal dynamics of soil moisture variability within a small agricultural maize cropped field. J Hydrol 261:86-101. doi:10.1016/S0022-1694(02)00016-1 10.1016/S0022-1694(02)00016-1

Ji R, Zhang S, Zheng L, Liu Q (2017) Prediction of soil moisture based on multilayer neural network with multi-valued neurons. Trans Chin Soc Agric Eng 33:126-131. doi:10.11975/j.issn.1002-6819.2017.z1.019 10.11975/j.issn.1002-6819.2017.z1.019

Kwon SH, Kim DH, Kim JS, Jung KY, Lee SH, Kwon JK (2020) Soil water flow patterns due to distance of two emitters of surface drip irrigation for horticultural crops. Hortic Sci Technol 38:631-644. doi:10.7235/HORT.20200058 10.7235/HORT.20200058

Lamorski K, Pastuszka T, Krzyszczak J, Sławiński C, Witkowska-Walczak B (2013) Soil water dynamic modeling using the physical and support vector machine methods. Vadose Zone J 12:1-12. doi:10.2136/vzj2013.05.0085 10.2136/vzj2013.05.0085

LeCun Y, Boser B, Denker JS, Henderson D, Howard RE, Hubbard W, Jackel LD (1989) Backpropagation applied to hand-written zip code recognition. Neural Comput 1:541-551. doi:10.1162/neco.1989.1.4.541 10.1162/neco.1989.1.4.541

Lewis-Beck C, Lewis-Beck M (2015) Multiple Regression: The Basics. In Applied Regression: An Introduction, Ed 2, Vol 22. Sage publications, California, USA, pp 55-74. doi:10.4135/9781483396774.n3 10.4135/9781483396774.n3

Lu CJ, Lee TS, Chiu CC (2009) Financial time series forecasting using independent component analysis and support vector regression. Decis Support Syst 47:115-125. doi:10.1016/j.dss.2009.02.001 10.1016/j.dss.2009.02.001

Lu T, Sun J, Wu K, Yang Z (2018) High-speed channel modeling with machine learning methods for signal integrity analysis. IEEE Trans Electromagn Compat 60:1957-1964. doi:10.1109/TEMC.2017.2784833 10.1109/TEMC.2017.2784833

Marshall CH, Pielke RA, Steyaert LT, Willard DA (2004) The impact of anthropogenic land-cover change on the Florida peninsula sea breezes and warm season sensible weather. Mon Weather Rev 132:28-52. doi:10.1175/1520-0493(2004)132<0028:TIOALC>2.0.CO;2 10.1175/1520-0493(2004)132<0028:TIOALC>2.0.CO;2

Matei O, Rusu T, Petrovan A, Mihuţ GA (2017) data mining system for real time soil moisture prediction. Procedia Eng 181:837-844. doi:10.1016/j.proeng.2017.02.475 10.1016/j.proeng.2017.02.475

McCabe MF, Wood EF, Wójcik R, Pan M, Sheffield J, Gao H, Su H (2008) Hydrological consistency using multi-sensor remote sensing data for water and energy cycle studies. Remote Sens Environ 112:430-444. doi:10.1016/j.rse.2007.03.027 10.1016/j.rse.2007.03.027

Montavon G, Samek W, Müller KR (2018) Methods for interpreting and understanding deep neural networks. Digit Signal Process 73:1-15. doi:10.1016/j.dsp.2017.10.011 10.1016/j.dsp.2017.10.011

Mushtaq R (2011) Augmented dickey fuller test. SSRN 1-19. doi:10.2139/ssrn.1911068 10.2139/ssrn.1911068

Nam S, Hong C, An SK, Kim J (2023) Low substrate water content is efficient for the performance of Ficus pumila 'Variegata' indoors. Hortic Environ Biotechnol 64:583-591. doi:10.1007/s13580-023-00514-1 10.1007/s13580-023-00514-1

Neitsch SL, Arnold JG, Kiniry JR, Williams JR (2011) Equations: Atmospheric Water. In Soil and Water Assessment Tool Theoretical Documentation Version 2009. Texas Water Resources Institute, Texas, USA, pp 51-64

Ntukamazina N, Onwonga RN, Sommer R, Mukankusi CM, Mburu J, Rubyogo JC (2017) Effect of excessive and minimal soil moisture stress on agronomic performance of bush and climbing bean (Phaseolus vulgaris L.). Cogent Food Agric 3:1373414. doi:10.1080/23311932.2017.1373414 10.1080/23311932.2017.1373414

Prasad R, Deo RC, Li Y, Maraseni T (2018) Soil moisture forecasting by a hybrid machine learning technique: ELM integrated with ensemble empirical mode decomposition. Geoderma 330:136-161. doi:10.1016/j.geoderma.2018.05.035 10.1016/j.geoderma.2018.05.035

Qi J, Du J, Siniscalchi SM, Ma X, Lee CH (2020) Analyzing upper bounds on mean absolute errors for deep neural net-work-based vector-to-vector regression. IEEE Trans Signal Process 68:3411-3422. doi:10.1109/TSP.2020.2993164 10.1109/TSP.2020.2993164

Qiu Y, Fu B, Wang J, Chen L (2001) Soil moisture variation in relation to topography and land use in a hillslope catchment of the Loess Plateau, China. J Hydrol 240:243-263. doi:10.1016/S0022-1694(00)00362-0 10.1016/S0022-1694(00)00362-0

Rushton KR, Eilers VHM, Carter RC (2006) Improved soil moisture balance methodology for recharge estimation. J Hydrol 318:379-399. doi:10.1016/j.jhydrol.2005.06.022 10.1016/j.jhydrol.2005.06.022

Shi CY, Liu L, Li QL, Wei ZF, Gao DT (2022) Comparison of drought resistance of rootstocks 'M9-T337' and 'M26' grafted with 'Huashuo' apple. Hortic Environ Biotechnol 63:299-310. doi:10.1007/s13580-021-00398-z 10.1007/s13580-021-00398-z

Šimůnek J, Van Genuchten MT (2008) Modeling nonequilibrium flow and transport processes using HYDRUS. Vadose Zone J 7:782-797. doi:10.2136/vzj2007.0074 10.2136/vzj2007.0074

Takagi K, Lin HS (2011) Temporal dynamics of soil moisture spatial variability in the shale hills critical zone observatory. Vadose Zone J 10:832-842. doi:10.2136/vzj2010.0134 10.2136/vzj2010.0134

Van Dam JC, Huygen J, Wesseling JG, Feddes RA, Kabat P, Van Walsum PEV, Groenendijk P, Van Diepen CA (1997) Soil Water Flow. In Theory of SWAP version 2.0; Simulation of water flow, solute transport and plant growth in the soil-water-atmosphere-plant environment. DLO Winand Staring Centre, Wageningen, Netherlands, pp 21-38

Wang Y, Yang J, Chen Y, Fang G, Duan W, Li Y, De Maeyer P (2019) Quantifying the effects of climate and vegetation on soil moisture in an arid area, China. Water 11:767. doi:10.3390/w11040767 10.3390/w11040767

Western AW, Grayson RB, Blöschl G, Willgoose GR, McMahon TA (1999) Observed spatial organization of soil moisture and its relation to terrain indices. Water Resour Res 35:797-810. doi:10.1029/1998WR900065 10.1029/1998WR900065

Williams AG, Ternan JL, Fitzjohn C, De Alba S, Perez-Gonzalez A (2003) Soil moisture variability and land use in a season-ally arid environment. Hydrol Process 17:225-235. doi:10.1002/hyp.1120 10.1002/hyp.1120

Wu CH, Ho JM, Lee DT (2004) Travel-time prediction with support vector regression. IEEE Trans Intell Transp Syst 5:276-281. doi:10.1109/TITS.2004.837813 10.1109/TITS.2004.837813

Xu XL, Ma KM, Fu BJ, Song CJ, Liu W (2008) Relationships between vegetation and soil and topography in a dry warm river valley, SW China. Catena 75:138-145. doi:10.1016/j.catena.2008.04.016 10.1016/j.catena.2008.04.016

Yan W, Zhou Q, Peng D, Wei X, Tang X, Yuan E, Wang Y, Shi C (2021) Soil moisture responses under different vegetation types to winter rainfall events in a humid karst region. Environ Sci Pollut 28:56984-56995. doi:10.1007/s11356-021-14620-z 10.1007/s11356-021-14620-z34085195

Yu J, Tang S, Zhangzhong L, Zheng W, Wang L, Wong A, Xu L (2020) A deep learning approach for multi-depth soil water content prediction in summer maize growth period. IEEE Access 8:199097-199110. doi:10.1109/ACCESS.2020.3034984 10.1109/ACCESS.2020.3034984

Yu J, Zhang X, Xu L, Dong J, Zhangzhong L (2021) A hybrid CNN-GRU model for predicting soil moisture in maize root zone. Agric Water Manag 245:106649. doi:10.1016/j.agwat.2020.106649 10.1016/j.agwat.2020.106649

Zhu Q, Lin H (2011) Influences of soil, terrain, and crop growth on soil moisture variation from transect to farm scales. Geoderma 163:45-54. doi:10.1016/j.geoderma.2011.03.015 10.1016/j.geoderma.2011.03.015

Information

Publisher :KOREAN SOCIETY FOR HORTICULTURAL SCIENCE
Publisher(Ko) :원예과학기술지
Journal Title :Horticultural Science and Technology
Journal Title(Ko) :원예과학기술지
Volume : 42
No :1
Pages :1-14
Received Date : 2023-06-21
Revised Date : 2023-09-08
Accepted Date : 2023-10-05
DOI :https://doi.org/10.7235/HORT.20240001

Horticultural Science and TechnologyISSN:1226-8763(Print) 2465-8588(Online)원예과학기술지

All Issue