Hourly sea level height forecast based on GNSS-IR by using ARIMA model

Zheng, Naiquan; Chai, Hongzhou; Ma, Yongchao; Chen, Lingqiu; Chen, Peng

doi:10.1080/01431161.2022.2091965

Cited by 15 publications

(7 citation statements)

References 41 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Simultaneously, the reconstructed tide level data are used to carry out the prediction research of tide level based on LSTM, and the best solution for prediction is explored through experiments. This study has also made significant improvements compared with previous work (Zheng et al., 2022). First of all, the sea level of the stations selected in this study did not show significant periodic changes, and this study confirmed that even if there is no good periodic change in sea level, it can still be predicted.…”

Section: Introductionmentioning

confidence: 74%

See 1 more Smart Citation

Hourly Sea Level Prediction‐Based GNSS‐IR Inversions by Combining the Least Squares Learning Cross‐Checking Method With the Gaussian Kernel Model L2 Constraint and LSTM

Zheng

Chai

et al. 2023

Earth and Space Science

Self Cite

View full text Add to dashboard Cite

Multisatellite systems and multi‐signal‐to‐noise ratio types provide a more prosperous data basis for the inversion of sea level by GNSS‐IR technology. However, there are few studies on data reconstruction of the retrieved sea level height. This study takes the SPBY station as an example and introduces the least squares learning cross‐checking method with the Gaussian kernel model (GKM) L2 constraint. Furthermore, research on hourly sea level reconstruction based on GNSS‐IR is carried out. Compared with the measured sea level, the sea level height in 2021 obtained after the fusion of multisource data has an R of 0.905 and an RMSE of 0.144 m. And the result obtained after data reconstruction has an R of 0.958 and an RMSE of 0.090 m. Compared with the multisource data fusion results before reconstruction, R is increased by 5.9%, and RMSE is decreased by 37.5%. Finally, using the reconstructed sea level data based on Long Short‐Term Memory (LSTM) artificial neural network to carry out the research on sea level prediction, which verifies the conclusion that more reliable forecast values can be obtained based on 5 months of training data. Among them, the R from 1 to 24 hr is 0.905, and the RMSE is 0.145 m. Compared with the inversion accuracy of GNSS‐IR, the R is increased by 2.0%, and the RMSE is decreased by 21.4%. This study demonstrates the feasibility of GNSS‐IR technology and L2‐constrained least squares learning cross‐checking method based on the GKM to reconstruct sea level data with high temporal resolution and high accuracy. The reliability of the sea level prediction based on GKM reconstruction and LSTM is verified in the sea level forecast of the next 24 epochs, which has essential applications in sea level data recovery and forecasting.

show abstract

Section: Introductionmentioning

confidence: 74%

“…Data from the German Research Centre for Geosciences (GFZ) archive with MGEX data’s precision ephemeris file (Zheng et al., 2022) were used in the creation of this manuscript. The facilities of SONEL and PSMSL (Zheng et al., 2021) were used for access to elevation datum conversion parameters.…”

Section: Data Availability Statementmentioning

confidence: 99%

Hourly Sea Level Prediction‐Based GNSS‐IR Inversions by Combining the Least Squares Learning Cross‐Checking Method With the Gaussian Kernel Model L2 Constraint and LSTM

Zheng

Chai

et al. 2023

Earth and Space Science

Self Cite

View full text Add to dashboard Cite

show abstract

“…Figure 3 takes Honor 60 as an example to show the diagram of GNSS-IR altimetry technology. To compare the measured height h and the retrieved height formula for effect during satellite signal propagation can be expressed as (Zhang et al 2017, Zheng et al 2022b, 2023:…”

Section: Basic Principle Of Gnss-ir Technologymentioning

confidence: 99%

Preliminary inquiry on the linear relationship between the height of the station and the ground height error retrieved by GNSS-IR with low-cost smart electronic equipment

Zheng,

Chai

2023

Meas. Sci. Technol.

Self Cite

View full text Add to dashboard Cite

Global Navigation Satellite System Interferometric Reflectometry (GNSS-IR) ground height retrieval technology is based on global navigation satellite system (GNSS) signal reflection, which can achieve efficient and high-precision ground retrieval. However, errors cannot be avoided. And whether there is a linear relationship between the height of the station and the error is unknown. This research uses Hi-Target geodetic GNSS receivers, smart phone devices (Honor 60) and smart tablet devices (Huawei MatePad Pro) to collect a total of 5 d data from DOY65 to DOY69 in 2023, with the station heights of 0.8 m, 1.0 m, 1.2 m, 1.4 m and 1.6 m, respectively. The experimental results show that each satellite can effectively establish a linear relationship between the inversion error and the station height, which can be used in the error compensation research of different station heights under the limitation that the height of reflector is between 0.8 m and 1.6 m. Simultaneously, the error is related to the influence of comprehensive factors such as reflector type, satellite number, and data-receiving equipment. Secondly, two clustering methods, k-means and k-media, are introduced to cluster a and b in the linear relationship y = ax + b of each satellite, and it is proved that the linear relationship between inversion error and station height is obviously related to ground reflection surface (plastic track and concrete ground). Finally, it is verified that the height measurement accuracy of low-cost smart electronic equipment (Root Mean Square Error (RMSE): 0.047 m and 0.042 m) is worse than that of GNSS (RMSE: 0.010 m), but it still has good measurement performance. All in all, this study provides an essential technical reference for the error compensation of different station heights and for the application of GNSS-IR with low-cost smart electronic equipment. Due to its low-cost advantage, it has great potential in developing other surface parameter inversion of GNSS-IR technology.

show abstract

“…For water level prediction, other methods based on time series analysis have also been used. These include ARIMA (Autoregressive Integrated Moving Average) [13], SARIMA (Seasonal Autoregressive Integrated Moving Averaged) [14], and Holtz-Winters Exponential Smoothing [15]. ARIMA achieved a root mean square error (RMSE) of 0.270 for one-dayahead prediction, while SARIMA and the Holt-Winters approach yielded RMSE values of 0.155 and 0.134, respectively, for seven-day-ahead forecasting.…”

Section: Introductionmentioning

confidence: 99%

Water Level Time Series Forecasting Using TCN Study Case in Surabaya

Saepudin,

Egi Shidqi Rabbani,

Dio Navialdy

et al. 2024

join

View full text Add to dashboard Cite

Climate change is causing water levels to rise, leading to detrimental effects like tidal flooding in coastal areas. Surabaya, the capital of East Java Province in Indonesia, is particularly vulnerable due to its low-lying location. According to the Meteorological, Climatological, and Geophysical Agency (BMKG), tidal flooding occurs annually in Surabaya as a result of rising water levels, highlighting the urgent need for water level forecasting models to mitigate these impacts. In this study, we employ the Temporal Convolutional Network (TCN) machine learning model for water level forecasting using data from a sea level station monitoring facility in Surabaya. We divided the training data into three scenarios: 3, 6, and 8 months to train TCN models for 14-day forecasts. The 8-month training scenario yielded the best results. Subsequently, we used the 8-month training data to forecast 1, 3, 7, and 14 days using TCN, Transformers, and the Recurrent Neural Network (RNN) models. TCN consistently outperformed other models, particularly excelling in 1-day forecasting with coefficient of determination () and RMSE values of 0.9950 and 0.0487, respectively.

show abstract

Hourly sea level height forecast based on GNSS-IR by using ARIMA model

Cited by 15 publications

References 41 publications

Hourly Sea Level Prediction‐Based GNSS‐IR Inversions by Combining the Least Squares Learning Cross‐Checking Method With the Gaussian Kernel Model L2 Constraint and LSTM

Hourly Sea Level Prediction‐Based GNSS‐IR Inversions by Combining the Least Squares Learning Cross‐Checking Method With the Gaussian Kernel Model L2 Constraint and LSTM

Preliminary inquiry on the linear relationship between the height of the station and the ground height error retrieved by GNSS-IR with low-cost smart electronic equipment

Water Level Time Series Forecasting Using TCN Study Case in Surabaya

Contact Info

Product

Resources

About