Neural network soil moisture model for irrigation scheduling

Sustainable freshwater management is underpinned by technologies which improve the efficiency of agricultural irrigation systems. Irrigation scheduling has the potential to incorporate real-time feedback from soil moisture and climatic sensors. However, for robust closed-loop decision support, models of the soil moisture dynamics are essential in order to predict crop water needs while adapting to external perturbation and disturbances. This paper presents a Dynamic Neural Network approach for modelling of the temporal soil moisture fluxes. The models are trained to generate a one-day-ahead prediction of the volumetric soil moisture content based on past soil moisture, precipitation, and climatic measurements. Using field data from three sites, a R 2 value above 0.94 was obtained during model evaluation in all sites. The models were also able to generate robust soil moisture predictions for independent sites which were not used in training the models. The application of the Dynamic Neural Network models in a predictive irrigation scheduling system was demonstrated using AQUACROP simulations of the potato-growing season. The predictive irrigation scheduling system was evaluated against a rule-based system that applies irrigation based on predefined thresholds. Results indicate that the predictive system achieves a water saving ranging between 20 and 46% while realizing a yield and water use efficiency similar to that of the rule-based system.

Download Full-text

Neural network models for soil moisture forecasting from remote sensed measurements

ACTA IMEKO ◽

10.21014/acta_imeko.v9i2.797 ◽

2020 ◽

Vol 9 (2) ◽

pp. 59

Author(s):

Andrea Marini ◽

Loris Francesco Termite ◽

Alberto Garinei ◽

Marcello Marconi ◽

Lorenzo Biondi

Keyword(s):

Neural Network ◽

Soil Moisture ◽

Short Term Memory ◽

Meteorological Data ◽

Network Models ◽

Irrigation Scheduling ◽

Machine Learning Techniques ◽

Free Access ◽

Neural Network Models ◽

Inference System

Machine learning techniques are employed to describe the temporal behavior of soil moisture using meteorological data as inputs. Three different Artificial Neural Network models, a feedforward Multi-Layer Perceptron, a Long-Short Term Memory and the Adaptive Network-based Fuzzy Inference System, are trained and their results are compared. The soil moisture is expressed in terms of Soil Water Index, derived from satellite retrievals, with the last known value also being used as input. The results are promising as the proposed methodology relies on free-access data with a worldwide coverage, allowing to easily estimate the forthcoming soil moisture. The knowledge of the expected value of this variable could be extremely useful for irrigation scheduling and it is the basis of Decision Support Systems to efficiently manage water resources in agriculture.

Download Full-text

CALIBRATION AND VERIFICATION OF THE SACRAMENTO SOIL MOISTURE MODEL ON THE SAN FRANCISQUITO CREEK WATERSHED

Hybrid Methods in Engineering ◽

10.1615/hybmetheng.v4.i1-2.20 ◽

2002 ◽

Vol 4 (1-2) ◽

pp. 22

Author(s):

William B. Mills ◽

Katherine H. Hancock

Keyword(s):

Soil Moisture ◽

Creek Watershed ◽

Soil Moisture Model ◽

Calibration And Verification

Download Full-text

Deep Learning Forecasts of Soil Moisture: Convolutional Neural Network and Gated Recurrent Unit Models Coupled with Satellite-Derived MODIS, Observations and Synoptic-Scale Climate Index Data

Remote Sensing ◽

10.3390/rs13040554 ◽

2021 ◽

Vol 13 (4) ◽

pp. 554

Author(s):

A. A. Masrur Ahmed ◽

Ravinesh C Deo ◽

Nawin Raj ◽

Afshin Ghahramani ◽

Qi Feng ◽

...

Keyword(s):

Neural Network ◽

Soil Moisture ◽

Deep Learning ◽

Convolutional Neural Network ◽

Climate Index ◽

Climate Indices ◽

High Temporal Resolution ◽

Synoptic Scale ◽

Time Step ◽

Gated Recurrent Unit

Remotely sensed soil moisture forecasting through satellite-based sensors to estimate the future state of the underlying soils plays a critical role in planning and managing water resources and sustainable agricultural practices. In this paper, Deep Learning (DL) hybrid models (i.e., CEEMDAN-CNN-GRU) are designed for daily time-step surface soil moisture (SSM) forecasts, employing the gated recurrent unit (GRU), complete ensemble empirical mode decomposition with adaptive noise (CEEMDAN), and convolutional neural network (CNN). To establish the objective model’s viability for SSM forecasting at multi-step daily horizons, the hybrid CEEMDAN-CNN-GRU model is tested at 1st, 5th, 7th, 14th, 21st, and 30th day ahead period by assimilating a comprehensive pool of 52 predictor dataset obtained from three distinct data sources. Data comprise satellite-derived Global Land Data Assimilation System (GLDAS) repository a global, high-temporal resolution, unique terrestrial modelling system, and ground-based variables from Scientific Information Landowners (SILO) and synoptic-scale climate indices. The results demonstrate the forecasting capability of the hybrid CEEMDAN-CNN-GRU model with respect to the counterpart comparative models. This is supported by a relatively lower value of the mean absolute percentage and root mean square error. In terms of the statistical score metrics and infographics employed to test the final model’s utility, the proposed CEEMDAN-CNN-GRU models are considerably superior compared to a standalone and other hybrid method tested on independent SSM data developed through feature selection approaches. Thus, the proposed approach can be successfully implemented in hydrology and agriculture management.

Download Full-text

CAS-LSM Datasets for the CMIP6 Land Surface Snow and Soil Moisture Model Intercomparison Project

Advances in Atmospheric Sciences ◽

10.1007/s00376-021-0293-x ◽

2021 ◽

Author(s):

Binghao Jia ◽

Longhuan Wang ◽

Yan Wang ◽

Ruichao Li ◽

Xin Luo ◽

...

Keyword(s):

Soil Moisture ◽

Land Surface ◽

Grid Point ◽

Global Ocean ◽

Surface Model ◽

Past Century ◽

Model Intercomparison ◽

Soil Moisture Model ◽

Surface Snow ◽

Intercomparison Project

AbstractThe datasets of the five Land-offline Model Intercomparison Project (LMIP) experiments using the Chinese Academy of Sciences Land Surface Model (CAS-LSM) of CAS Flexible Global-Ocean-Atmosphere-Land System Model Grid-point version 3 (CAS FGOALS-g3) are presented in this study. These experiments were forced by five global meteorological forcing datasets, which contributed to the framework of the Land Surface Snow and Soil Moisture Model Intercomparison Project (LS3MIP) of CMIP6. These datasets have been released on the Earth System Grid Federation node. In this paper, the basic descriptions of the CAS-LSM and the five LMIP experiments are shown. The performance of the soil moisture, snow, and land-atmosphere energy fluxes was preliminarily validated using satellite-based observations. Results show that their mean states, spatial patterns, and seasonal variations can be reproduced well by the five LMIP simulations. It suggests that these datasets can be used to investigate the evolutionary mechanisms of the global water and energy cycles during the past century.

Download Full-text