A 100 m annual soil salinization dataset from 1985 to 2024 in the Western Songnen Plain, China
<p><span lang="EN-US">In our study, we identified and classified soil salinization degrees in the Western Songnen Plain at 100 m spatial resolution using ground surveys data and remote sensing imagery, combined with machine learning algorithms over the period 1985 to 2024.</span></p> <p><span lang="EN-US"> </span></p> <p><strong><span lang="EN-US">The publicly available data used in this paper, as well as the modeling code, are shown below: </span></strong></p> <p><span lang="EN-US">1) </span><span lang="EN-US">The remote sensing satellite data used in this study are freely available on GEE platform (available at </span><span lang="EN-US"><a href="https://code.earthengine.google.com/">https://code.earthengine.google.com/</a></span><span lang="EN-US">). </span></p> <p><span lang="EN-US">2) </span><span lang="EN-US">Land cover data can be accessed at </span><span lang="EN-US"><a href="https://doi.org/10.5281/zenodo.4417810">https://doi.org/10.5281/zenodo.4417810</a></span><span lang="EN-US">. </span></p> <p><span lang="EN-US">3) </span><span lang="EN-US">SSSG dataset is available at </span><span lang="EN-US"><a href="https://files.isric.org/public/global_soil_salinity/salmap1986/" target="_blank" rel="noopener">https://files.isric.org/public/global_soil_salinity</a></span><span lang="EN-US">. </span></p> <p><span lang="EN-US">4) </span><span lang="EN-US">LDSS data are available at </span><span lang="EN-US"><a href="https://doi.org/10.6084/m9.figshare.13295918.v1">https://doi.org/10.6084/m9.figshare.13295918.v1</a></span><span lang="EN-US">. </span></p> <p><span lang="EN-US">5) </span><span lang="EN-US">Yearly identification results of saline soils are available at </span><span lang="EN-US"><a href="https://code.earthengine.google.com/3dd47875d7455825297b9a6a8766a8ee">https://code.earthengine.google.com/3dd47875d7455825297b9a6a8766a8ee</a></span><span lang="EN-US">. </span></p> <p><span lang="EN-US">6) </span><span lang="EN-US">The data required for model inputs (TIR</span>、<span lang="EN-US">SIT</span>、<span lang="EN-US">PDI) are available at</span> <span lang="EN-US"><a href="https://code.earthengine.google.com/7fc0e7ee2cf4cb6b744aaf4706a140c9">https://code.earthengine.google.com/7fc0e7ee2cf4cb6b744aaf4706a140c9</a>.</span></p> <p><span lang="EN-US"> </span></p> <p><strong><span lang="EN-US">The presented data file contains:</span></strong></p> <p><span lang="EN-US">1) </span><span lang="EN-US">Soil EC sampling points</span></p> <p><span lang="EN-US">2) </span><span lang="EN-US">TIRSITPDI_predicted.mat</span></p> <p><span lang="EN-US">3) </span><span lang="EN-US">Soil_EC_prediction_model.m</span></p> <p><span lang="EN-US">4) </span><span lang="EN-US">Statistical results of soil salinization degree by area (1985-2024)</span></p> <p><span lang="EN-US">5) </span><span lang="EN-US">Yearly degree of soil salinization (1985-2024)</span></p> <p><span lang="EN-US">6) </span><span lang="EN-US">Yearly identification results of saline soils (1985-2024)</span></p> <p><span lang="EN-US">7) </span><span lang="EN-US">Yearly soil EC results (1985-2024)</span></p> <p><span lang="EN-US"> </span></p> <p><strong><span lang="EN-US">Samples:</span></strong></p> <p><span lang="EN-US">The file, Soil_EC_sampling_points.csv, provides essential information on 942 sample points.</span> <span lang="EN-US">Below are the descriptions for each column in the metadata:</span></p> <ul> <li><span lang="EN-US"> </span><span lang="EN-US">Municipal: Location where the point is located </span></li> <li><span lang="EN-US"> </span><span lang="EN-US">LnEC: The observed LnEC</span> <span lang="EN-US">using a conductivity meter (Light Magnetic, model: DDS-307A).</span></li> <li><span lang="EN-US"> </span><span lang="EN-US">TIR</span>、<span lang="EN-US">SIT</span>、<span lang="EN-US">PDI:<strong> </strong>Characteristic parameters in the models.</span></li> </ul> <p><span lang="EN-US"> </span></p> <p><strong><span lang="EN-US">Models:</span></strong></p> <p><span lang="EN-US">We trained on this data using eight models (NNF, GPR, LSBoost, KPLS, Tree, SVM, LR, and SVM Kernel) from the Matlab (R2024a) Toolbox.</span> <span lang="EN-US">To optimize the NNF for accurate soil salinity estimation (R² = 0.467; RMSE = 0.729 dS m⁻¹), we trained the model using nested loops and fine-tuned parameters such as the training algorithm, the number of hidden layer nodes, and the learning rate. After 14,000 rounds of cycling, the optimal model </span><span lang="EN-US">TIRSITPDI_predicted.mat</span><span lang="EN-US"> is finally obtained. Finally, the </span><span lang="EN-US">characteristic parameters</span><span lang="EN-US"> with the model are put into </span><span lang="EN-US">Soil_EC_prediction_model.m</span><span lang="EN-US"> to obtain the soil salinity values.</span></p> <p><span lang="EN-US"> </span></p> <p><strong><span lang="EN-US">Results:</span></strong></p> <ul> <li><span lang="EN-US">Statistical results of soil salinization degree by area (1985-2024) shows</span> <span lang="EN-US">statistical results for each class (Slightly, Moderately, Highly, Extremely) as well as total saline acreage in the Western Sonnen Plain for the years 1985-2024.</span></li> <li><span lang="EN-US">Yearly degree of soil salinization (1985-2024) presents the results of saline soil classification based on the U.S. Salinity Laboratory’s classification system for the </span><span lang="EN-US">Western Sonnen Plain</span><span lang="EN-US"> from 1985-2024. </span></li> <li><span lang="EN-US">Yearly identification results of saline soils (1985-2024) displays the results of saline soil identification in the </span><span lang="EN-US">Western Sonnen Plain</span><span lang="EN-US"> from 1985-2024.</span></li> <li><span lang="EN-US">Yearly soil EC results (1985-2024) exhibits the results of model-predicted soil EC content in the </span><span lang="EN-US">Western Sonnen Plain</span><span lang="EN-US"> for the years 1985-2024.</span></li> </ul>
ShareScore
16/100
Overall dataset sharing score
Score breakdown
These five areas show where the dataset supports — or may limit — practical reuse.
- Stewardship
- 4
- Harmonization
- 4
- Access
- 8
- Reuse readiness
- 0
- Engagement
- 0
ScienceDex for faculty
Your academic CV and NIH biosketch
Make your CV in your school's format and your NIH biosketch from it, then download both as Word files.