FRINK Linked Data Fragments server

Matches in SemOpenAlex for { <https://semopenalex.org/work/W4313594090> ?p ?o ?g. }

• W4313594090 endingPage "116321" @default.
• W4313594090 startingPage "116321" @default.
• W4313594090 abstract "Soil salinization is a major environmental risk caused by natural or human activities especially in arid and semi-arid regions. Machine learning for rapidly monitoring large-scale spatial soil salinization becomes possible. However, machine learning often needs large training samples and obtaining extensive soil salinization information by field investigation is laborious and difficult. In practice, the field soil sampling datasets are often sparse and non-normally distributed. The intricacy of features extracted from remote sensing images increases the model complexity and often leads to degradation in the prediction performance. To solve this problem, an integrative framework is proposed to predict soil salt content (SSC) based on light gradient boosting machine (LGBM). In this model, we first introduce the data augmentation method (Mixup) to improve sample diversity and alleviate model overfitting by the sparsity of samples. To improve the generalization and robustness of the model in different spatial heterogeneity of soil salinization, the Mixup-LGBM model is adaptively and jointly optimized by combining hyperparameters and feature selection in a Bayesian optimization framework. Furthermore, model interpretability is improved using shapley additive explanations (SHAP) value based on the combination of the confidence of the synthetic data through model visualization and feature importance assessment. In addition, different cases are simulated to test the model performance. In Case I, the raw sample-sparsity model using the data augmentation algorithm has higher prediction accuracy than other unused models. In Case Ⅱ, the extreme sample-sparsity model still achieves satisfactory results while the other models can’t learn any effective information after multiple iterations. The experimental results reveal that the proposed model can automatically find representative features in heterogeneous environments and has strong adaptability in different study areas. This finding indicates that digital elevation model (DEM) has a high influence on SSC in both study areas. Besides the DEM, soil salinization in the Manasi River Basin is more sensitive to human activities, while that in the Werigan–Kuqa River Delta Oasis is more sensitive to natural factors. The Mixup-LGBM model is suitable for predicting SSC in different sample sparsity scenarios while ensuring the high accuracy. The model has considerable potential for dealing with other complex sample sparsity regression tasks." @default.
• W4313594090 created "2023-01-06" @default.
• W4313594090 creator A5002454695 @default.
• W4313594090 creator A5004077064 @default.
• W4313594090 creator A5004229339 @default.
• W4313594090 creator A5008171524 @default.
• W4313594090 creator A5045535750 @default.
• W4313594090 creator A5060002817 @default.
• W4313594090 creator A5073418500 @default.
• W4313594090 creator A5075132661 @default.
• W4313594090 creator A5078727362 @default.
• W4313594090 creator A5081055268 @default.
• W4313594090 date "2023-02-01" @default.
• W4313594090 modified "2023-10-12" @default.
• W4313594090 title "Integrative modeling of heterogeneous soil salinity using sparse ground samples and remote sensing images" @default.
• W4313594090 cites W1821210865 @default.
• W4313594090 cites W1993783251 @default.
• W4313594090 cites W2012686349 @default.
• W4313594090 cites W2031600437 @default.
• W4313594090 cites W2034334268 @default.
• W4313594090 cites W2040611841 @default.
• W4313594090 cites W2088765131 @default.
• W4313594090 cites W2096990904 @default.
• W4313594090 cites W2104487864 @default.
• W4313594090 cites W2129888542 @default.
• W4313594090 cites W2130615363 @default.
• W4313594090 cites W2192203593 @default.
• W4313594090 cites W2344920982 @default.
• W4313594090 cites W2555206945 @default.
• W4313594090 cites W2599561306 @default.
• W4313594090 cites W2618369426 @default.
• W4313594090 cites W2761380721 @default.
• W4313594090 cites W2762355583 @default.
• W4313594090 cites W2769706980 @default.
• W4313594090 cites W2792956321 @default.
• W4313594090 cites W2888238379 @default.
• W4313594090 cites W2890179699 @default.
• W4313594090 cites W2891975230 @default.
• W4313594090 cites W2893301845 @default.
• W4313594090 cites W2895435696 @default.
• W4313594090 cites W2911964244 @default.
• W4313594090 cites W2981674946 @default.
• W4313594090 cites W2994645803 @default.
• W4313594090 cites W2999615587 @default.
• W4313594090 cites W3005372647 @default.
• W4313594090 cites W3006286553 @default.
• W4313594090 cites W3014009018 @default.
• W4313594090 cites W3015398416 @default.
• W4313594090 cites W3023943971 @default.
• W4313594090 cites W3028009715 @default.
• W4313594090 cites W3083577680 @default.
• W4313594090 cites W3092124659 @default.
• W4313594090 cites W3111588349 @default.
• W4313594090 cites W3128666714 @default.
• W4313594090 cites W3136869765 @default.
• W4313594090 cites W3159845116 @default.
• W4313594090 cites W3179991324 @default.
• W4313594090 cites W3183269215 @default.
• W4313594090 cites W3204034810 @default.
• W4313594090 cites W3214210612 @default.
• W4313594090 cites W4200008654 @default.
• W4313594090 cites W4200201691 @default.
• W4313594090 cites W4200450964 @default.
• W4313594090 cites W4205572600 @default.
• W4313594090 cites W4210877154 @default.
• W4313594090 cites W4211230577 @default.
• W4313594090 cites W4214672600 @default.
• W4313594090 cites W4307823382 @default.
• W4313594090 cites W751077916 @default.
• W4313594090 doi "https://doi.org/10.1016/j.geoderma.2022.116321" @default.
• W4313594090 hasPublicationYear "2023" @default.
• W4313594090 type Work @default.
• W4313594090 citedByCount "1" @default.
• W4313594090 countsByYear W43135940902023 @default.
• W4313594090 crossrefType "journal-article" @default.
• W4313594090 hasAuthorship W4313594090A5002454695 @default.
• W4313594090 hasAuthorship W4313594090A5004077064 @default.
• W4313594090 hasAuthorship W4313594090A5004229339 @default.
• W4313594090 hasAuthorship W4313594090A5008171524 @default.
• W4313594090 hasAuthorship W4313594090A5045535750 @default.
• W4313594090 hasAuthorship W4313594090A5060002817 @default.
• W4313594090 hasAuthorship W4313594090A5073418500 @default.
• W4313594090 hasAuthorship W4313594090A5075132661 @default.
• W4313594090 hasAuthorship W4313594090A5078727362 @default.
• W4313594090 hasAuthorship W4313594090A5081055268 @default.
• W4313594090 hasBestOaLocation W43135940901 @default.
• W4313594090 hasConcept C119857082 @default.
• W4313594090 hasConcept C124101348 @default.
• W4313594090 hasConcept C141650431 @default.
• W4313594090 hasConcept C154945302 @default.
• W4313594090 hasConcept C159390177 @default.
• W4313594090 hasConcept C159750122 @default.
• W4313594090 hasConcept C22019652 @default.
• W4313594090 hasConcept C2781067378 @default.
• W4313594090 hasConcept C39432304 @default.
• W4313594090 hasConcept C41008148 @default.
• W4313594090 hasConcept C50644808 @default.
• W4313594090 hasConceptScore W4313594090C119857082 @default.

• next