Modeling for the Prediction of Soil Moisture in Litchi Orchard with Deep Long Short-Term Memory

Soil moisture is an important factor determining yield. With the increasing demand for agricultural irrigation water resources, evaluating soil moisture in advance to create a reasonable irrigation schedule would help improve water resource utilization. This paper established a continuous system for collecting meteorological information and soil moisture data from a litchi orchard. With the acquired data, a time series model called Deep Long Short-Term Memory (Deep-LSTM) is proposed in this paper. The Deep-LSTM model has five layers with the fused time series data to predict the soil moisture of a litchi orchard in four different growth seasons. To optimize the data quality of the soil moisture sensor, the Symlet wavelet denoising algorithm was applied in the data preprocessing section. The threshold of the wavelets was determined based on the unbiased risk estimation method to obtain better sensor data that would help with the model learning. The results showed that the root mean square error (RMSE) values of the Deep-LSTM model were 0.36, 0.52, 0.32, and 0.48%, and the mean absolute percentage error (MAPE) values were 2.12, 2.35, 1.35, and 3.13%, respectively, in flowering, fruiting, autumn shoots, and flower bud differentiation stages. The determination coefficients (R2) were 0.94, 0.95, 0.93, and 0.94, respectively, in the four different stages. The results indicate that the proposed model was effective at predicting time series soil moisture data from a litchi orchard. This research was meaningful with regards to acquiring the soil moisture characteristics in advance and thereby providing a valuable reference for the litchi orchard’s irrigation schedule.

Comparison of Field and SAR-Derived Descriptors in the Retrieval of Soil Moisture from Oil Palm Crops Using PALSAR-2

Synthetic-aperture radar’s (SAR’s) capacity to resolve the cloud cover concerns encountered while gathering optical data has tremendous potential for soil moisture data retrieval using SAR data. It is possible to use SAR data to recover soil moisture because the backscatter coefficient is sensitive to both soil and vegetation by penetrating through the vegetation layer. This study investigated the feasibility of employing a SAR-derived radar vegetation index (RVI), the ratios of the backscatter coefficients using polarizations of HH/HV (RHH/HV) and HV/HH (RHH/HV) to an oil palm crops as vegetation indicators in the water cloud model (WCM) using phased-array L-band SAR-2 (PALSAR-2). These data were compared to the manual leaf area index (LAI) and a physical soil sampling method for computing soil moisture. The field data included the LAI input parameters and, more importantly, physical soil samples from which to calculate the soil moisture. The fieldwork was carried out in Chuping District, Perlis State, Malaysia. Corresponding PALSAR-2 data were collected on three observation dates in 2019: 17 January, 16 April, and 9 July. The results showed that the WCM modeled using the LAI under HV polarization demonstrated promising accuracy, with the root mean square error recorded as 0.033 m3/m3. This was comparable to the RVI and RHH/HV under HV polarization, which had accuracies of 0.031 and 0.049 m3/m3, respectively. The findings of this study suggest that SAR-based indicators, RHH/HV and RVI using PALSAR-2, can be used to reduce field-related input in the retrieval of soil moisture data using the WCM for oil palm crop.

Modelling soil organic carbon turnover with assimilation of satellite soil moisture data

The content of organic carbon is one of the essential factors that define soil quality. It is also notoriously challenging to model due to a multitude of biological and abiotic factors influencing the process. In this study, we investigate how decomposition of soil organic matter is affected by soil moisture and temperature. Soil organic carbon turnover is simulated by the CENTURY model. The accuracy of soil moisture data used is ensured by data assimilation approach, combing mathematical model and satellite retrievals. Numerical experiments demonstrate the influence of soil moisture regimes and climate on the quantity of soil humus stocks.

Assessment of the Temperature Effects in SMAP Satellite Soil Moisture Products in Oklahoma

Soil moisture is a notably important component in various studies in water sciences, including hydrology, agriculture, and water management. To achieve extensive or global spatial coverage, satellites focusing on soil moisture observation have been launched, and many satellite products, such as SMAP and SMOS soil moisture products, have been provided. Most of these satellite observations are based on the dielectric properties of wet soil, and most soil moisture retrieval algorithms are calibrated or evaluated using in situ soil moisture. While the in situ data observed by dielectric sensors, which are the most widely used, are reported to include errors caused by the so-called “temperature effects” of these sensors, the temperature dependency of bulk soil dielectric constant has rarely been discussed on satellite data. Since both in situ dielectric measurements and satellite observations are based on the same physical variable, the dielectric constant and the dielectrically measured in situ soil moisture data are also used as ground truth, it is necessary to assess the impact of temperature effects on satellite products. In this work, we attempted to identify the existence of the temperature effects and evaluate the consequences of removing these effects on in situ and satellite soil moisture and the relationships between the brightness temperature at the soil surface and the brightness temperature provided by satellite observation. To achieve the goals of this study, we analyzed the temperature effects on surface soil moisture data provided by a SMAP mission in Oklahoma, the United States. The results show that temperature effects exist in SMAP soil moisture products in Oklahoma, and the removal of these effects will potentially improve the accuracy of these products.

Passive Microwave Remote Sensing Soil Moisture Data in Agricultural Drought Monitoring: Application in Northeastern China

Drought is the costliest disaster around the world and in China as well. Northeastern China is one of China’s most important major grain producing areas. Frequent droughts have harmed the agriculture of this region and further threatened national food security. Therefore, the timely and effective monitoring of drought is extremely important. In this study, the passive microwave remote sensing soil moisture data, i.e., the SMOS soil moisture (SMOS-SM) product, was compared to several in situ meteorological indices through Pearson correlation analysis to assess the performance of SMOS-SM in monitoring drought in northeastern China. Then, maps based on SMOS-SM and in situ indices were created for July from 2010 to 2015 to identify the spatial pattern of drought distributions. Our results showed that the SMOS-SM product had relatively high correlation with in situ indices, especially SPI and SPEI values of a nine-month scale for the growing season. The drought patterns shown on maps generated from SPI-9, SPEI-9 and sc-PDSI were also successfully captured using the SMOS-SM product. We found that the SMOS-SM product effectively monitored drought patterns in northeastern China, and this capacity would be enhanced when field capacity information became available.

Soil moisture data using citizen science technology cross-validated by satellite data

Soil moisture represents many attributes of the geo-hydrological cycle and the climate system. Citizen science through social media as an emerging tool could be utilized to collect soil moisture data. A pilot study area was selected in Shahriar, Iran. A user interface and a sampling process (use of citizen science by subscribers) were designed to analyze the subjective and gravimetric soil moisture data. Furthermore, explanatory moisture condition (EMC), a new initiative to consider land use in soil moisture information from vegetation cover, was evaluated. A statistical artificial neural network was used for quantifying subjective data, and soil moisture layouts were produced by utilizing the ordinary kriging (OK) method. For cross-validating, the land surface temperature data from the MODIS satellite were retrieved. A platform for the region with 200 m grids resolution to collect daily soil moisture at eight ungauged stations is proposed to utilize subjective data from the subscribers and cross-validated with satellite data. A virtual station at the centroid of the pervious part of the study area was selected as a reference station for data collection daily or weekly to generate soil moisture time series. The results showed a high potential of utilizing satellite and citizen science data for real-time estimation of scarce soil moisture data in developing regions.