A dual-branch network soil moisture inversion method based on TM-01 data

Abstract

This paper discloses a dual-branch network soil moisture inversion method based on TM-01 data, which relates to the field of soil moisture remote sensing inversion technology. The basic steps are: temporally and spatially matching TM-01 satellite data with SMAP satellite soil moisture product data; normalizing and quality controlling the matched training and validation samples; analyzing the importance of data features using the XGBoost machine learning method and removing three features of low importance; inputting the optimized sample data and validation data into a fully connected neural network and random forest model to establish a model and invert soil moisture results; and finally fusing the soil moisture inversion results of the two models using a weighted average method to obtain the final soil moisture inversion result. This method has the advantages of objective and reasonable satellite observation data and high soil moisture inversion accuracy.

Description

Technical Field

[0001] The present invention relates to the technical field of soil moisture remote sensing inversion, and in particular to a double-branch network soil moisture inversion method based on TM-01 data. Background Art

[0002] Soil moisture is a key variable connecting the water cycle and ecological energy exchange between land and atmosphere, and is closely related to agricultural production, climate regulation, and hydrological processes. Accurate monitoring of soil moisture is of great significance for drought detection, climate change prediction, and water resources management. Currently, optical remote sensing and passive microwave remote sensing are the main technical means for large-scale soil moisture observation. Optical remote sensing satellite data provides high spatial resolution but is easily affected by interference from clouds and vegetation; passive microwave remote sensing data has high temporal resolution but low spatial resolution. Passive microwave remote sensing technology, represented by the Soil Moisture Active Probe Satellite (SMAP), can provide global soil moisture data at a resolution of 36 kilometers and a revisit period of 2-3 days. However, for some hydrological and climate applications, soil moisture data with higher temporal and spatial resolution remains an urgent need.

[0003] With the development of GNSS-R technology, it has shown great potential as an alternative to traditional soil moisture monitoring methods. GNSS-R offers advantages such as global coverage, low cost, insensitivity to weather conditions, near-real-time data acquisition, and short satellite revisit times. In soil moisture retrieval, surface characteristics such as vegetation cover and roughness lead to a nonlinear relationship between GNSS-R signals and surface soil moisture. Compared to linear models, machine learning and deep learning models are better able to capture these complex relationships. Currently, most GNSS-R soil moisture retrieval research is based on TechDemoSat-1 (TDS-1) and Cyclone Global Navigation Satellite System (CYGNSS) satellite data, and no research based on TM-01 satellite data has been reported. Therefore, this paper utilizes TM-01 satellite data and proposes a dual-branch network soil moisture retrieval method based on TM-01 data, providing technical support for soil moisture monitoring based on TM-01 data. Summary of the Invention

[0004] The present invention provides a dual-branch network soil moisture inversion method based on TM-01 data, which effectively improves the accuracy of soil moisture inversion under complex surface conditions and provides a new technical path and data support for soil moisture monitoring.

[0005] According to one aspect of the present disclosure, a dual-branch network soil moisture inversion method based on TM-01 data is provided, comprising the following steps:

[0006] (1) Acquire TM-01 satellite data and SMAP satellite soil moisture product data; match the TM-01 satellite data and SMAP satellite soil moisture product data in time and space to generate training samples and validation samples with a ratio of 7:3. Temporal matching refers to matching the data of the same date of the TM-01 satellite data and the SMAP satellite soil moisture product data. Spatial matching refers to matching the TM-01 satellite data and the SMAP satellite soil moisture product data using the nearest neighbor method, that is, retaining the point with the closest latitude and longitude between the TM-01 satellite data mirror reflection point and the SMAP satellite soil moisture product data grid point for spatial matching;

[0007] (2) Preprocessing operations on training samples and validation samples, including normalization and quality control processing; quality control processing includes removing low-quality reflection points and water areas;

[0008] (3) Use XGBoost machine learning to analyze the importance of information features in the training sample and verification sample data, and remove the three features with low importance;

[0009] (4) Establish a fully connected neural network model. By selecting the relu activation function, data batch normalization, L2 regularization, dropout and fully connected network parameter settings, the training sample data and validation sample data with low-importance features removed are input into the fully connected neural network. After multiple iterations, the soil moisture inversion result y1 and the root mean square error RMSE1 are obtained;

[0010] (5) Establish a random forest model. By setting the number of decision trees, the maximum depth of decision trees, the maximum number of features, the minimum number of samples for internal nodes, the minimum number of samples for leaf nodes, the evaluation criteria, and the sample sampling method, the training sample data and the validation samples with low-importance features removed are input into the random forest model to obtain the soil moisture inversion results y2 and the root mean square error RMSE2;

[0011] (6) The weighted average method is used to calculate the soil moisture inversion results y1, y2 and the root mean square errors RMSE1 and RMSE2 to obtain the final soil moisture inversion results.

[0012] In one possible implementation, in step (6), the weighted average method is used to calculate the soil moisture inversion results y1, y2 and the root mean square errors RMSE1, RMSE2 to obtain the final soil moisture inversion result y. The calculation formula is:

[0013] ;

[0014] Among them, the unit of the inversion result y is cm 3 / cm 3 .

[0015] Compared with the prior art, the present invention has the following beneficial effects:

[0016] This disclosure discloses a dual-branch network soil moisture inversion method based on TM-01 data. Current GNSS-R-based soil moisture inversion research focuses primarily on TDS-1 and CYGNSS satellite data, with no research utilizing TM-01 satellite data. By leveraging TM-01 satellite data and leveraging a dual-branch network, this method fully exploits the potential of TM-01 satellite data, effectively improving the accuracy of soil moisture inversion under complex surface conditions and providing new technical approaches and data support for soil moisture monitoring. BRIEF DESCRIPTION OF THE DRAWINGS

[0017] Figure 1 A flowchart of a dual-branch network soil moisture inversion method based on TM-01 data according to an embodiment of the present disclosure is shown.

[0018] Figure 2 A soil moisture inversion accuracy diagram according to an embodiment of the present disclosure is shown. DETAILED DESCRIPTION

[0019] Various exemplary embodiments, features, and aspects of the present disclosure will be described in detail below with reference to the accompanying drawings. The same reference numerals in the accompanying drawings represent elements with the same or similar functions. Although various aspects of the embodiments are shown in the accompanying drawings, the drawings are not necessarily drawn to scale unless otherwise indicated.

[0020] The word “exemplary” is used exclusively herein to mean “serving as an example, example, or illustration.” Any embodiment described herein as “exemplary” is not necessarily to be construed as preferred or advantageous over other embodiments.

[0021] In addition, numerous specific details are provided in the following detailed description to better illustrate the present disclosure. Those skilled in the art will appreciate that the present disclosure can be practiced without certain specific details. In some instances, methods, means, components, and circuits well known to those skilled in the art are not described in detail in order to highlight the main points of the present disclosure.

[0022] According to one aspect of the present disclosure, a dual-branch network soil moisture inversion method based on TM-01 data is provided, comprising the following steps:

[0023] (1) Acquire TM-01 satellite data and SMAP satellite soil moisture product data; match the TM-01 satellite data and SMAP satellite soil moisture product data in time and space to generate training samples and validation samples with a ratio of 7:3. Temporal matching refers to matching the data of the same date of the TM-01 satellite data and the SMAP satellite soil moisture product data. Spatial matching refers to matching the TM-01 satellite data and the SMAP satellite soil moisture product data using the nearest neighbor method, that is, retaining the point with the closest latitude and longitude between the TM-01 satellite data mirror reflection point and the SMAP satellite soil moisture product data grid point for spatial matching;

[0024] (2) Preprocessing operations on training samples and validation samples, including normalization and quality control processing; quality control processing includes removing low-quality reflection points and water areas;

[0025] (3) Use XGBoost machine learning to analyze the importance of information features in the training sample and verification sample data, and remove the three features with low importance;

[0026] (4) Establish a fully connected neural network model FCNN. By selecting the relu activation function, data batch normalization, L2 regularization, dropout and fully connected network parameter settings, the training sample data with low-importance features removed and the validation sample data are input into the fully connected neural network. After multiple iterations, the soil moisture inversion result y1 and the root mean square error RMSE1 are obtained;

[0027] (5) Establish a random forest model RF. By setting the number of decision trees, the maximum depth of decision trees, the maximum number of features, the minimum number of samples for internal nodes, the minimum number of samples for leaf nodes, the evaluation criteria, and the sample sampling method, the training sample data and the validation samples with low-importance features removed are input into the random forest model to obtain the soil moisture inversion results y2 and the root mean square error RMSE2.

[0028] (6) The weighted average method is used to calculate the soil moisture inversion results y1, y2 and the root mean square errors RMSE1 and RMSE2 to obtain the final soil moisture inversion results.

[0029] This disclosure discloses a dual-branch network soil moisture inversion method based on TM-01 data. Current GNSS-R-based soil moisture inversion research focuses primarily on TDS-1 and CYGNSS satellite data, with no research utilizing TM-01 satellite data. By leveraging TM-01 satellite data and leveraging a dual-branch network, this method fully exploits the potential of TM-01 satellite data, effectively improving the accuracy of soil moisture inversion under complex surface conditions and providing new technical approaches and data support for soil moisture monitoring.

[0030] In one possible implementation, in step (6), the weighted average method is used to calculate the soil moisture inversion results y1, y2 and the root mean square errors RMSE1, RMSE2 to obtain the final soil moisture inversion result y. The calculation formula is:

[0031] ;

[0032] Among them, the unit of the inversion result y is cm 3 / cm 3 .

[0033] like Figure 2 As shown in FIG, it is a scatter plot of the soil moisture inversion results obtained by the double-branch network soil moisture inversion method based on TM-01 data described in this embodiment. Figure 2 As shown in the figure, the x-axis represents soil moisture from the SMAP satellite, and the y-axis represents predicted soil moisture. The diagonal line y = x, with a sample size of 83,156, has a root mean square error (RMSE) of 0.0409, and the goodness of fit (R) of the linear regression is 0.84. The goodness of fit function is y = 0.703x + 0.03.

[0034] While various embodiments of the present disclosure have been described above, the foregoing description is intended to be illustrative, non-exhaustive, and not limited to the disclosed embodiments. Many modifications and variations will be apparent to those skilled in the art without departing from the scope and spirit of the described embodiments. The terminology used herein is selected to best explain the principles of the embodiments, their practical applications, or technological improvements in the marketplace, or to enable others skilled in the art to understand the embodiments disclosed herein.

Claims

1. A dual-branch network soil moisture inversion method based on TM-01 data, characterized in that: The following steps are involved: (1) Acquire TM-01 satellite data and SMAP satellite soil moisture product data; match the TM-01 satellite data and SMAP satellite soil moisture product data in time and space to generate training samples and validation samples with a ratio of 7:

3. Temporal matching refers to matching the data of the same date of the TM-01 satellite data and the SMAP satellite soil moisture product data. Spatial matching refers to matching the TM-01 satellite data and the SMAP satellite soil moisture product data using the nearest neighbor method, that is, retaining the point with the closest latitude and longitude between the TM-01 satellite data mirror reflection point and the SMAP satellite soil moisture product data grid point for spatial matching; (2) Preprocessing operations on training samples and validation samples, including normalization and quality control processing; quality control processing includes removing low-quality reflection points and water areas; (3) Use XGBoost machine learning to analyze the importance of information features in the training sample and verification sample data, and remove the three features with low importance; (4) Establish a fully connected neural network model. By selecting the relu activation function, data batch normalization, L2 regularization, dropout and fully connected network parameter settings, the training sample data and validation sample data with low-importance features removed are input into the fully connected neural network. After multiple iterations, the soil moisture inversion result y1 and the root mean square error RMSE1 are obtained; (5) Establish a random forest model. By setting the number of decision trees, the maximum depth of decision trees, the maximum number of features, the minimum number of samples for internal nodes, the minimum number of samples for leaf nodes, the evaluation criteria, and the sample sampling method, the training sample data and the validation samples with low-importance features removed are input into the random forest model to obtain the soil moisture inversion results y2 and the root mean square error RMSE2; (6) The weighted average method is used to calculate the soil moisture inversion results y1, y2 and the root mean square errors RMSE1 and RMSE2 to obtain the final soil moisture inversion results.

2. A dual-branch network soil moisture inversion method based on TM-01 data according to claim 1, characterized in that: In step (6), the weighted average method is used to calculate the soil moisture inversion results y1, y2 and the root mean square errors RMSE1 and RMSE2 to obtain the final soil moisture inversion result y. The calculation formula is: ； Among them, the unit of the inversion result y is cm 3 / cm 3 .

Images