FRINK Linked Data Fragments server

Matches in SemOpenAlex for { <https://semopenalex.org/work/W4304193076> ?p ?o ?g. }

• W4304193076 endingPage "159387" @default.
• W4304193076 startingPage "159387" @default.
• W4304193076 abstract "Heavy metal contamination is ubiquitous in brownfields. Traditional site investigation employs geostatistical interpolation methods (GIMs) to predict the distribution of soil pollutants after soil sampling and chemical analysis. However, the heterogeneity of soil pollution in brownfields makes the assumptions of GIMs no longer valid and further undermines the accuracy of soil investigation. In the present study, a satellite hyperspectral image processing and machine learning method was developed to map arsenic pollution at a brownfield site. To eliminate the noise caused by atmospheric factors and increase the efficiency of spectral data, 1.3 million spectral indexes (SIs) were constructed and 1171 of them were selected due to their high correlations with soil arsenic. Five machine learning methods, i.e., Random forest (RF), ExtraTrees, Adaptive Boosting, Extreme Gradient Trees, and Gradient Descent Boosting Trees (GDB) were built to predict soil arsenic. The RF method was found to render the best performance (r = 0.78), reducing 30 % of prediction errors compared with traditional GIMs. RF also maintained a relatively higher level of accuracy (r = 0.56) when the sampling grids increased to 100 m, which was higher than that of GIMs under a 50 m sampling grid (r = 0.42), revealing that the proposed method can provide more accurate results with fewer sampling points, namely less investigation cost. It was indicated that the second derivate was the most efficient preprocessing method to remove spectral noise and normalized difference (ND) was the most reliable spectral index construction strategy. Based on uncertainty analysis, the heterogeneity of soil arsenic distribution was considered the most influential factor causing prediction errors. This study demonstrates that machine learning based on satellite visible and near-infrared reflectance spectroscopy (VNIR) is a promising approach to map soil arsenic contamination at brownfield sites with high accuracy and low cost." @default.
• W4304193076 created "2022-10-11" @default.
• W4304193076 creator A5043898206 @default.
• W4304193076 creator A5065266286 @default.
• W4304193076 date "2023-01-01" @default.
• W4304193076 modified "2023-09-26" @default.
• W4304193076 title "Mapping soil arsenic pollution at a brownfield site using satellite hyperspectral imagery and machine learning" @default.
• W4304193076 cites W1975230218 @default.
• W4304193076 cites W1988898310 @default.
• W4304193076 cites W1989763695 @default.
• W4304193076 cites W1994610198 @default.
• W4304193076 cites W1995060534 @default.
• W4304193076 cites W2001569762 @default.
• W4304193076 cites W2004132785 @default.
• W4304193076 cites W2005709478 @default.
• W4304193076 cites W2013290860 @default.
• W4304193076 cites W2025857348 @default.
• W4304193076 cites W2028400289 @default.
• W4304193076 cites W2037275106 @default.
• W4304193076 cites W2046206266 @default.
• W4304193076 cites W2056132907 @default.
• W4304193076 cites W2063246330 @default.
• W4304193076 cites W2084778007 @default.
• W4304193076 cites W2090021199 @default.
• W4304193076 cites W2090517596 @default.
• W4304193076 cites W2100176513 @default.
• W4304193076 cites W2147037083 @default.
• W4304193076 cites W2172063876 @default.
• W4304193076 cites W2261059368 @default.
• W4304193076 cites W2320628436 @default.
• W4304193076 cites W2558714883 @default.
• W4304193076 cites W2560192201 @default.
• W4304193076 cites W2565188411 @default.
• W4304193076 cites W2755905524 @default.
• W4304193076 cites W2760888259 @default.
• W4304193076 cites W2767663224 @default.
• W4304193076 cites W2769330703 @default.
• W4304193076 cites W2780172228 @default.
• W4304193076 cites W2784260830 @default.
• W4304193076 cites W2788165206 @default.
• W4304193076 cites W2800441203 @default.
• W4304193076 cites W2804146571 @default.
• W4304193076 cites W2883827111 @default.
• W4304193076 cites W2884471890 @default.
• W4304193076 cites W2908218487 @default.
• W4304193076 cites W2911964244 @default.
• W4304193076 cites W2945020384 @default.
• W4304193076 cites W2946066539 @default.
• W4304193076 cites W2948816905 @default.
• W4304193076 cites W2951969386 @default.
• W4304193076 cites W2966045283 @default.
• W4304193076 cites W2968496090 @default.
• W4304193076 cites W2969092494 @default.
• W4304193076 cites W2995099525 @default.
• W4304193076 cites W3004687548 @default.
• W4304193076 cites W3029887509 @default.
• W4304193076 cites W3037428236 @default.
• W4304193076 cites W3093016721 @default.
• W4304193076 cites W3093191653 @default.
• W4304193076 cites W3111017134 @default.
• W4304193076 cites W3111257695 @default.
• W4304193076 cites W3127186305 @default.
• W4304193076 cites W3128629046 @default.
• W4304193076 cites W3130979562 @default.
• W4304193076 cites W3131177540 @default.
• W4304193076 cites W3133828512 @default.
• W4304193076 cites W3161773888 @default.
• W4304193076 cites W3170168490 @default.
• W4304193076 cites W3172651349 @default.
• W4304193076 cites W3195297080 @default.
• W4304193076 cites W3204104536 @default.
• W4304193076 cites W3204758132 @default.
• W4304193076 cites W3208302850 @default.
• W4304193076 cites W3208364360 @default.
• W4304193076 cites W3211332754 @default.
• W4304193076 cites W3213071502 @default.
• W4304193076 cites W3214880743 @default.
• W4304193076 cites W3216428451 @default.
• W4304193076 cites W4212883601 @default.
• W4304193076 cites W906019740 @default.
• W4304193076 doi "https://doi.org/10.1016/j.scitotenv.2022.159387" @default.
• W4304193076 hasPubMedId "https://pubmed.ncbi.nlm.nih.gov/36240926" @default.
• W4304193076 hasPublicationYear "2023" @default.
• W4304193076 type Work @default.
• W4304193076 citedByCount "5" @default.
• W4304193076 countsByYear W43041930762023 @default.
• W4304193076 crossrefType "journal-article" @default.
• W4304193076 hasAuthorship W4304193076A5043898206 @default.
• W4304193076 hasAuthorship W4304193076A5065266286 @default.
• W4304193076 hasConcept C106131492 @default.
• W4304193076 hasConcept C127313418 @default.
• W4304193076 hasConcept C140779682 @default.
• W4304193076 hasConcept C159078339 @default.
• W4304193076 hasConcept C159390177 @default.
• W4304193076 hasConcept C178790620 @default.
• W4304193076 hasConcept C185592680 @default.
• W4304193076 hasConcept C18903297 @default.
• W4304193076 hasConcept C31972630 @default.

• next