High variation topsoil pollution forecasting in the Russian Subarctic: Using artificial neural networks combined with residual kriging

Tarasov, Dmitry; Buevich, Alexander; Sergeev, Alexander; Shichkin, Andrey

doi:10.1016/j.apgeochem.2017.07.007

Cited by 58 publications

(25 citation statements)

References 29 publications

Supporting

Mentioning

Contrasting

Unclassified

Order By: Relevance

“…Первый, обучающий, традиционно вклю-чающий большую часть данных (в нашем случае первые 168 отсчетов), использован для обучения сети. На основании нашего опыта и работ других авторов оптимальным соотношением обучающей и тестовой подвыборок является 70:30 [21][22][23][24][25][26][27]…”

Section: материалы и методыunclassified

Two-step combined algorithm for improving the accuracy of predicting methane concentration in atmospheric air based on the NARX neural network and subsequent prediction of residuals

Subbotina¹,

Buevich²,

Sergeev³

et al. 2020

AEE

Self Cite

View full text Add to dashboard Cite

Институт промышленной экологии Уральского отделения РАН (Екатеринбург, Российская Федерация) М. С. Ремезова Уральский федеральный университет им. первого Президента России Б. Н. Ельцина (Екатеринбург, Российская Федерация) Статья поступила в редакцию 19 ноября 2019 г. Предложен двухшаговый комбинированный алгоритм прогнозирования концентрации метана в атмосферном воздухе, основанный на использовании искусственных нейронных сетей и последующем моделировании невязок. Для выбора базовой модели проведено сравнение результатов двух наиболее часто применяемых для прогноза временных рядов искусственных нейронных сетей: нелинейной авторегрессионной нейронной сети с внешним входом NARX и нейронной сети Elman. Временной ряд составлен из значений концентрации метана в приземном слое атмосферного воздуха, полученных при экологическом мониторинге парниковых газов на арктическом острове Белый (Россия). Выбран временной интервал 192 ч в течение летнего периода, характеризующийся значительными суточными колебаниями концентрации метана. Для обучения нейронной сети использованы значения, соответствующие первым 168 ч интервала, следующие 24 ч были спрогнозированы. Точность прогноза оценивалась на основе ряда рассчитываемых показателей: индексов согласия, абсолютной ошибки, среднеквадратической и среднеквадратичной относительной ошибки. Предложенный алгоритм позволил повысить точность прогноза лучшей базовой модели NARX по всем показателям.

show abstract

Section: материалы и методыunclassified

Two-step combined algorithm for improving the accuracy of predicting methane concentration in atmospheric air based on the NARX neural network and subsequent prediction of residuals

Subbotina¹,

Buevich²,

Sergeev³

et al. 2020

AEE

Self Cite

View full text Add to dashboard Cite

show abstract

“…The combination of different approaches makes it possible to improve the accuracy of forecasting. For example, hybrids ANN and kriging have been used successfully in studies [16]- [18].…”

Section: -1mentioning

confidence: 99%

Multilayer perceptron, generalized regression neural network, and hybrid model in predicting the spatial distribution of impurity in the topsoil of urbanized area

Subbotina

Buevich

Shichkin

et al. 2018

AIP Conference Proceedings

View full text Add to dashboard Cite

The study is based on the data obtained as a result of soil screening in the city of Noyabrsk, Russia. A comparison of two types of neural networks most commonly used in this type of research was carried out: multi-layer perceptron (MLP), generalized regression neural network (GRNN), and a combined MLP and ordinary kriging approach (MLPRK) for predicting the spatial distribution of the chemical element Chromium (Cr) in the surface layer of the urbanized territory. The model structures were developed using computer modeling, based on minimizing of a root mean squared error (RMSE). As input parameters, the spatial coordinates were used, and the concentration of Cr-as the output. The hybrid MLPRK approach showed the best prognostic accuracy.

show abstract

“…After the re-design to predict quantitative outputs and solve regression problems, this algorithm came to be the support vector machine for regression (SVR) and acquired wide successes in stand volume modeling [19,20]. Hybrid approaches involve either the statistical regression or machine learning model between the target variable and remote sensing predictors, interpolating residuals of predictions by kriging, and combining them [21][22][23]. Those two-step approaches both consider the spatial heterogeneity conveyed by remote sensing predictors and autocorrelation of neighboring observed data [24,25].…”

Section: Introductionmentioning

confidence: 99%

Multi-Sensor Prediction of Stand Volume by a Hybrid Model of Support Vector Machine for Regression Kriging

Chen

Ren

Zhang

et al. 2020

Forests

View full text Add to dashboard Cite

Quantifying stand volume through open-access satellite remote sensing data supports proper management of forest stand. Because of limitations on single sensor and support vector machine for regression (SVR) as well as benefits from hybrid models, this study innovatively builds a hybrid model as support vector machine for regression kriging (SVRK) to map stand volume of the Changbai Mountains mixed forests covering 171,450 ha area based on a small training dataset (n = 928). This SVRK model integrated SVR and its residuals interpolated by ordinary kriging. To determine the importance of multi-sensor predictors from ALOS and Sentinel series, the increase in root mean square error (RMSE) of SVR was calculated by removing the variable after the standardization. The SVRK model achieved accuracy with mean error, RMSE and correlation coefficient in -2.67%, 25.30% and 0.76, respectively, based on an independent dataset (n = 464). The SVRK improved the accuracy of 9% than SVR based on RMSE values. Topographic indices from L band InSAR, backscatters of L band SAR, and texture features of VV channel from C band SAR, as well as vegetation indices of the optical sensor were contributive to explain spatial variations of stand volume. This study concluded that SVRK was a promising approach for mapping stand volume in the heterogeneous temperate forests with limited samples.

show abstract

High variation topsoil pollution forecasting in the Russian Subarctic: Using artificial neural networks combined with residual kriging

Cited by 58 publications

References 29 publications

Two-step combined algorithm for improving the accuracy of predicting methane concentration in atmospheric air based on the NARX neural network and subsequent prediction of residuals

Two-step combined algorithm for improving the accuracy of predicting methane concentration in atmospheric air based on the NARX neural network and subsequent prediction of residuals

Multilayer perceptron, generalized regression neural network, and hybrid model in predicting the spatial distribution of impurity in the topsoil of urbanized area

Multi-Sensor Prediction of Stand Volume by a Hybrid Model of Support Vector Machine for Regression Kriging

Contact Info

Product

Resources

About