Effects of vegetation and soil texture on surface soil moisture retrieval using multi-temporal optical and thermal infrared observations

This paper explores the accuracy in using an artificial neural network (ANN) to estimate root-zone soil moisture (RZSM) at multiple worldwide locations using only in situ surface soil moisture (SSM) as a training dataset. The paper also addresses the transferability of the trained ANN across climatic and soil texture conditions. Data from the International Soil Moisture Network (ISMN) were collected for several networks with variable soil texture and climate classes. Several scaling, feature extraction, and training approaches were tested. An artificial neural network employing rolling averages (ANNRAV) of SSM over 10, 30, and 90 days was developed. The results show that applying a standard scaling (SSCA) to the ANN input features improves the correlation, Nash–Sutcliffe efficiency (NSE), and root mean square error (RMSE) for 52%, 91%, and 87%, respectively, of the tested stations, compared to MinMax scaling (MMSCA). Different training sets are suggested, namely, training on data from all networks, data from one network, or data of all networks excluding one. Based on these trainings, new transferability (TranI) and contribution (ContI) indices are defined. The results show that one network cannot provide the best prediction accuracy if used alone to train the ANN. They also show that the removal of the less contributing networks enhances performance. For example, elimination of the densest network (SCAN) from the training enhances the mean correlation by 20.5% and the mean NSE by 42.5%. This motivates the implementation of a data filtering technique based on the ANN’s performance. A median, max, and min correlation of 0.77, 0.96, and 0.65, respectively, are obtained by the model after data filtering. The performances are also analyzed with respect to the covered climatic regions and soil texture, providing insights into the robustness and limitations of the approach, namely, the need for complementary information in highly evaporative regions. In fact, the ANN using only SSM to predict RZSM has low performance when decoupling between the surface and root zones is observed. The application of ANN to obtain spatialized RZSM will require integrating remote sensing-based surface soil moisture in the future.

Download Full-text

Controls on surface soil drying rates observed by SMAP and simulated by the Noah land surface model

10.5194/hess-2017-338 ◽

2017 ◽

Author(s):

Peter J. Shellito ◽

Eric E. Small

Keyword(s):

Soil Moisture ◽

Soil Texture ◽

Vegetation Cover ◽

Land Surface ◽

Surface Soil ◽

Surface Model ◽

Soil Drying ◽

Potential Evaporation ◽

Surface Soil Moisture ◽

Drying Rates

Abstract. Drydown periods that follow precipitation events provide an opportunity to assess the mechanisms by which soil moisture dissipates from the land surface. We use SMAP (Soil Moisture Active Passive) observations and Noah simulations from drydown periods to quantify the role of soil moisture, potential evaporation, vegetation cover, and soil texture on soil drying rates. Rates are determined using finite differences over intervals of 1 to 3 days. In the Noah model, the drying rates are a good approximation of direct soil evaporation rates. Data cover the domain of the North American Land Data Assimilation System phase 2 and span the first 1.8 years of SMAP's operation. Drying of surface soil moisture observed by SMAP is faster than that simulated by Noah. SMAP drying is fastest when surface soil moisture levels are high, potential evaporation is high, and when vegetation cover is low. Soil texture plays a minor role in SMAP drying rates. Noah simulations show similar responses to soil moisture and potential evaporation, but vegetation has a minimal effect and soil texture has a much larger effect compared to SMAP. When drying rates are normalized by potential evaporation, SMAP observations and Noah simulations both show that increases in vegetation cover lead to decreases in evaporative efficiency from the surface soil. However, the magnitude of this effect simulated by Noah is much weaker than that determined from SMAP observations.

Download Full-text