Studies on predicting soil moisture levels at Andhra Loyola College, India, using SARIMA and LSTM models

Kumar, M. Tanooj; Rao, M. C.

doi:10.1007/s10661-023-12080-1

Cited by 2 publications

(3 citation statements)

References 22 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…They also found the LSTM model superior in terms of accuracy (R 2 = 0.99). These models were also univariate models[75].The LSTM model in this study has a high R 2 value similar to the aforementioned studies. Moreover, the inclusion of atmospheric variables alongside subsurface VWC is essential due to the high correlation in the time series analysis and forecastability tests.…”

supporting

confidence: 81%

“…That study was conducted only using soil water content of different soil depths [74]. A comparison between the seasonal autoregressive integrated moving average (SARIMA) and the LSTM model to forecast soil moisture profiles was conducted by Kumar and Rao (2023). They also found the LSTM model superior in terms of accuracy (R 2 = 0.99).…”

Section: Discussionmentioning

confidence: 99%

“…They also found the LSTM model superior in terms of accuracy (R 2 = 0.99). These models were also univariate models [75].…”

Section: Discussionmentioning

confidence: 99%

See 2 more Smart Citations

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

Basir,

Noel,

Buckmaster

et al. 2024

Agriculture

View full text Add to dashboard Cite

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 R2, MAE (m3m−3), MSE (m6m−6), and RMSE (m3m−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 R2, MAE (m3m−3), MSE (m6m−6), and RMSE (m3m−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.

show abstract

supporting

confidence: 81%

Section: Discussionmentioning

confidence: 99%