Forecasting contamination in an ecosystem based on a network model.

This paper aims to predict heavy metal pollution based on ecological factors with a new approach, using artificial neural networks (ANNs), by significantly removing typical obstacles like time-consuming laboratory procedures and high implementation costs. Pollution prediction is crucial for the safety of all living things, for sustainable development, and for policymakers to make the right decisions. This study focuses on predicting heavy metal contamination in an ecosystem at a significantly lower cost because pollution assessment still primarily relies on conventional methods, which are recognized to have disadvantages. To accomplish this, the data collected for 800 plant and soil materials have been utilized in the production of an ANN. This research is the first to use an ANN to predict pollution very accurately and has found the network models to be very suitable systemic tools for modelling in pollution data analysis. The findings appear are promising to be very illuminating and pioneering for scientists, conservationists, and governments to swiftly and optimally develop their appropriate work programs to leave a functioning ecosystem for all living things. It has been observed that the relative errors calculated for each of the polluting heavy metals for training, testing, and holdout data are significantly low.

An investigation on environmental pollution due to essential heavy metals: a prediction model through multilayer perceptrons.

This research is to predict heavy metal levels in plants, particularly in Robinia pseudoacacia L., and soils using an effective artificial intelligence approach with some ecological parameters, thereby significantly eliminating common defects such as high cost and seriously tedious and time-consuming laboratory procedures. In this respect, the artificial neural network (ANN) is employed to estimate the concentrations of essential heavy metals such as Fe, Mn and Ni, depending on the Cu and Zn concentrations of plant and soil samples collected from five different locations. The derived relative errors for the constructed ANN model have been computed within the ranges 0.041-0.051, 0.017-0.025, and 0.026-0.029 for the training, testing and holdout data regarding Fe, Mn, and Ni, respectively. In addition, it has been realized that the relative errors could be diminished up to 0.007 for Fe, 0.014 for Mn and 0.022 for Ni by considering the Cu, Zn, location and plant parts as independent variables during the analysis. The results produced seem instructive and pioneering for environmentalists and scientists to design optimal study programs to leave a livable ecosystem.

The levels of essential heavy metals, Fe, Mn, Ni, based on Zn and Cu in plant and soil samples have been predicted through an AI-based prediction model, a class of feedforward artificial neural networks (ANNs) with a multilayer perceptron (MLP). Thereby common drawbacks such as high cost and severely time-consuming laboratory procedures have been significantly eradicated. In the evaluation of different pollution levels at locations, it has been shown that the ANN method can overcome several disadvantages of analytical element analyzers to monitor the amounts of heavy metals such as Fe, Mn, and Ni in soil and plants.