Artificial neural network modeling in environmental radioactivity studies – A review

Dragović, Snežana

doi:10.1016/j.scitotenv.2022.157526

Cited by 26 publications

(6 citation statements)

References 125 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Soils have been contaminated for much longer than anticipated by normal ssion product radionuclides such 137 Cs and 90 Sr. A long time aer the initial contamination, radioactive nuclei like 40 K, 90 Sr, 137 Cs, 232 Th, and 238 U, as well as some radioactive wastes produced by nuclear reactors, are readily bio-available in the soil prole and are absorbed by plants, making them available for further dispersion within food chains. 33…”

Section: Radioisotopesmentioning

confidence: 99%

Natural surfactant mediated bioremediation approaches for contaminated soil

Sar,

Kundu,

Ghosh

et al. 2023

RSC Adv.

View full text Add to dashboard Cite

show abstract

Section: Radioisotopesmentioning

confidence: 99%

Natural surfactant mediated bioremediation approaches for contaminated soil

Sar,

Kundu,

Ghosh

et al. 2023

RSC Adv.

View full text Add to dashboard Cite

show abstract

“…Backpropagation-type ANNs are based on the ability of the algorithm to minimize prediction errors by repeatedly repropagating those errors from the output layer to the input layer (Mouloodi et al 2022). ANNs backpropagation starts its training process with a forward propagation (Dragović 2022), then propagates the signals from the seven input parameters to predict the photosynthetic rate. Based on the ANNs parameters, the model is trained by trial and error using the normalized training dataset on the input-hidden-output structure.…”

Section: Anns Development Model With Inputs Variation Scenariosmentioning

confidence: 99%

Photosynthetic Rate Prediction Model of Golden Melon Plant (Cucumis melo L.) at Vegetative Phase in Greenhouse using Artificial Neural Networks

Erniati,

Suhardiyanto,

Hasbullah

et al. 2023

HAYATI J Biosci

View full text Add to dashboard Cite

The most critical parameter affecting plant growth is the photosynthetic rate. The parameter can be determined by measuring the rate of CO2 assimilation that occurs in plants. Developing a photosynthetic rate model can recommend proper cultivation maintenance in melon plants. Hence, the involvement of input parameters in the developed model affects the accuracy of the prediction. This study aims to develop an artificial neural networks (ANNs) prediction model of the photosynthetic rate of melon plants in the vegetative phase in the greenhouse based on seven environmental and growth parameters and find the best model structure. Model development uses artificial neural networks with several stages: data collection and pre-processing, model development with different input variations, model validation, and selection of the best scenario to predict photosynthetic rate. The results showed that five out of seven input parameters, i.e., air temperature, sunlight intensity, CO2 concentration, air humidity, and plant rows, in the model structure of five inputs, six hidden and one output were the best model scenarios with coefficient of determination (R2) and root mean square error (RMSE) of 0.986 and 0.420, respectively.

show abstract

“…According to Dragović (2022) [87], the training consists of synaptic weights modification between the different neurons in order to reduce the error between the real and the predicted value for the training cases. In fact, the modification of the synaptic weights is carried out by means of learning algorithms [87]. There are different training algorithms, but, according to Dragović (2022) [87], the backpropagation (BP) algorithm is the most used [88,89].…”

Section: Artificial Neural Networkmentioning

confidence: 99%

“…In fact, the modification of the synaptic weights is carried out by means of learning algorithms [87]. There are different training algorithms, but, according to Dragović (2022) [87], the backpropagation (BP) algorithm is the most used [88,89].…”

Section: Artificial Neural Networkmentioning

confidence: 99%

Assessment of Different Machine Learning Methods for Reservoir Outflow Forecasting

Soria-Lopez,

Sobrido-Pouso,

Mejuto

et al. 2023

Water

View full text Add to dashboard Cite

Reservoirs play an important function in human society due to their ability to hold and regulate the flow. This will play a key role in the future decades due to climate change. Therefore, having reliable predictions of the outflow from a reservoir is necessary for early warning systems and adequate water management. In this sense, this study uses three approaches machine learning (ML)-based techniques—Random Forest (RF), Support Vector Machine (SVM) and artificial neural network (ANN)—to predict outflow one day ahead of eight different dams belonging to the Miño-Sil Hydrographic Confederation (Galicia, Spain), using three input variables of the current day. Mostly, the results obtained showed that the suggested models work correctly in predicting reservoir outflow in normal conditions. Among the different ML approaches analyzed, ANN was the most appropriate technique since it was the one that provided the best model in five reservoirs.

show abstract

Artificial neural network modeling in environmental radioactivity studies – A review

Cited by 26 publications

References 125 publications

Natural surfactant mediated bioremediation approaches for contaminated soil

Natural surfactant mediated bioremediation approaches for contaminated soil

Photosynthetic Rate Prediction Model of Golden Melon Plant (Cucumis melo L.) at Vegetative Phase in Greenhouse using Artificial Neural Networks

Assessment of Different Machine Learning Methods for Reservoir Outflow Forecasting

Contact Info

Product

Resources

About