Enhancing Subsurface Soil Moisture Forecasting: A Long Short-Term Memory Network Model Using Weather Data

Md. Samiul Basir (), Samuel Noel, Dennis Buckmaster and Muhammad Ashik-E-Rabbani
Additional contact information
Md. Samiul Basir: Department of Agricultural and Biological Engineering, Purdue University, West Lafayette, IN 47907, USA
Samuel Noel: Department of Agricultural and Biological Engineering, Purdue University, West Lafayette, IN 47907, USA
Dennis Buckmaster: Department of Agricultural and Biological Engineering, Purdue University, West Lafayette, IN 47907, USA
Muhammad Ashik-E-Rabbani: Department of Farm Power and Machinery, Bangladesh Agricultural University, Mymensingh 2202, Bangladesh

Agriculture, 2024, vol. 14, issue 3, 1-24

Abstract: Subsurface soil moisture is a primary determinant for root development and nutrient transportation in the soil and affects the tractability of agricultural vehicles. A statistical forecasting model, Vector AutoRegression (VAR), and a Long Short-Term Memory network (LSTM) were developed to forecast the subsurface soil moisture at a 20 cm depth using 9 years of historical weather data and subsurface soil moisture data from Fort Wayne, Indiana, USA. A time series analysis showed that the weather data and soil moisture have a stationary seasonal tendency and demonstrated that soil moisture can be forecasted from weather data. The VAR model estimates volumetric soil moisture of one-day ahead with an R 2 , MAE (m 3 m −3 ), MSE (m 6 m −6 ), and RMSE (m 3 m −3 ) of 0.698, 0.0561, 0.0046, and 0.0382 for 2021 corn cropping season, whereas the LSTM model using inputs of previous seven days yielded R 2 , MAE (m 3 m −3 ), MSE (m 6 m −6 ), and RMSE (m 3 m −3 ) of 0.998, 0.00237, 0.00002, and 0.00382, respectively as tested for cropping season of 2020 and 0.973, 0.00368, 0.00003 and 0.00577 as tested for the cropping season of 2021. The LSTM model presents a viable data-driven alternative to traditional statistical models for forecasting subsurface soil moisture.

Keywords: forecastability; historical data; LSTM; time series analysis; VAR; weather data integration (search for similar items in EconPapers)
JEL-codes: Q1 Q10 Q11 Q12 Q13 Q14 Q15 Q16 Q17 Q18 (search for similar items in EconPapers)
Date: 2024
References: View references in EconPapers View complete reference list from CitEc
Citations:

Downloads: (external link)
https://www.mdpi.com/2077-0472/14/3/333/pdf (application/pdf)
https://www.mdpi.com/2077-0472/14/3/333/ (text/html)

Related works:
This item may be available elsewhere in EconPapers: Search for items with the same title.

Export reference: BibTeX RIS (EndNote, ProCite, RefMan) HTML/Text

Persistent link: https://EconPapers.repec.org/RePEc:gam:jagris:v:14:y:2024:i:3:p:333-:d:1342371

Access Statistics for this article

Agriculture is currently edited by Ms. Leda Xuan

More articles in Agriculture from MDPI
Bibliographic data for series maintained by MDPI Indexing Manager ().