Testing the applicability of random forest modeling to examine benthic foraminiferal responses to multiple environmental parameters

Coupling process-based modeling with machine learning for long-term simulation of wastewater treatment plant operations

Effective treatment of sewage by wastewater treatment plants (WWTPs) are essential to protecting water environment as well as people's health worldwide. However, operation of WWTPs is usually intricate due to precarious influent characteristics and nonlinear sewage treatment processes. Effective modeling of WWTPs can provide valuable decision-making support to facilitate their daily operations and management. In this study, we have built a novel hybrid model by combining a process-based WWTP model (GPS-X) with a data-driven machine learning model (Random Forest) to improve the simulation of long-term hourly effluent ammonium-nitrogen concentration of a WWTP. Our study results have shown that the hybrid GPS-X-RF model performs the best with a coefficient of determination (R²) of 0.95 and root mean squared error (RMSE) of 0.23 mg/L, followed by the GPS-X model with a R² of 0.93 and RMSE of 0.33 mg/L and last the Random Forest model with a R² of 0.84 and RMSE of 0.41 mg/L. Capable of incorporating wastewater treatment mechanisms and utilizing superior data mining capabilities of machine learning, the hybrid model adapts better to the large fluctuations in influent and operating conditions of the WWTP. The proposed hybrid modeling framework may be easily extended to WWTPs of various size and types to simulate their operations under increasingly variable environmental and operating conditions.

Inferring the ecological quality status based on living benthic foraminiferal indices in transitional areas of the Guanabara bay (SE Brazil)

Using benthic foraminifera, we evaluate the ecological quality status (EcoQS) of transitional waters of the Guanabara Bay (SE Brazil) by applying the diversity-based index exp (H'_bc) and the sensitivity-based Foram-AMBI for the first time in South America. The Guanabara Bay was selected for this study as it is one of the largest transitional ecosystems in the State of Rio de Janeiro and has been severely impacted by anthropogenic activities. Concentrations of potentially toxic elements (PTEs) were assessed by sequential chemical extraction in three phases (i.e., dissolved in water, adsorbed on organic matter, and Mn oxy-hydroxides). Total organic carbon, total nitrogen, and stable isotope (δ¹³C and δ¹⁵N) signatures of organic matter were analyzed to trace environmental stress. The Ammonia/Elphidium ratio suggests hypoxic conditions at most of the sampled sites. Principal component analysis identifies the first component as environmental stress underlying organic matter and PTE enrichment (in all three phases), which is positively related to Foram-AMBI and negatively to exp (H'_bc). The exp (H'_bc) and Foram-AMBI indices reveal that stations near the Governador Island and Niterói margin have the worst EcoQS, showing medium to extreme pollution. Additionally, Foram-AMBI and exp (H'_bc) provide a congruent EcoQS classification for ∼64% of the sites. Although these results are promising, they suggest that a significant effort should be made to obtain better knowledge of foraminiferal ecological requirements to employ benthic foraminifera as a biomonitoring and management method.

A novel intelligent displacement prediction model of karst tunnels

Karst is a common engineering environment in the process of tunnel construction, which poses a serious threat to the construction and operation, and the theory on calculating the settlement without the assumption of semi-infinite half-space is lack. Meanwhile, due to the limitation of test conditions or field measurement, the settlement of high-speed railway tunnel in Karst region is difficult to control and predict effectively. In this study, a novel intelligent displacement prediction model, following the machine learning (ML) incorporated with the finite difference method, is developed to evaluate the settlement of the tunnel floor. A back propagation neural network (BPNN) algorithm and a random forest (RF) algorithm are used herein, while the Bayesian regularization is applied to improve the BPNN and the Bayesian optimization is adopted for tuning the hyperparameters of RF. The newly proposed model is employed to predict the settlement of Changqingpo tunnel floor, located in the southeast of Yunnan Guizhou Plateau, China. Numerical simulations have been performed on the Changqingpo tunnel in terms of variety of karst size, and locations. Validations of the numerical simulations have been validated by the field data. A data set of 456 samples based on the numerical results is constructed to evaluate the accuracy of models’ predictions. The correlation coefficients of the optimum BPNN and BR model in testing set are 0.987 and 0.925, respectively, indicating that the proposed BPNN model has more great potential to predict the settlement of tunnels located in karst areas. The case study of Changqingpo tunnel in karst region has demonstrated capability of the intelligent displacement prediction model to well predict the settlement of tunnel floor in Karst region.

Benthic foraminifera as proxies for the environmental quality assessment of the Kuwait Bay (Kuwait, Arabian Gulf): Morphological and metabarcoding approaches

The rapid urbanization and industrialization of Kuwait and the consequent effluent discharges into marine environments have resulted in a degradation of water and sediment quality in the coastal marine ecosystems such as in the Kuwait Bay. This study investigates the ecological response of benthic foraminifera (protists) to environmental stress in the Kuwait Bay. The traditional morphological approach was compared to the innovative environmental DNA (eDNA) metabarcoding to evaluate the ecological quality status (EcoQS). Forty-six surface sediment samples were collected from selected stations in the Kuwait Bay. To detect the pollution gradient, environmental parameters from water (e.g., salinity, pH, dissolved oxygen) and sediment (e.g., grain-size, trace metals, total organic carbon, total petroleum hydrocarbons) were measured at each station. Although the foraminiferal assemblages were different in the morphological and molecular datasets, the species turnover was congruent and statistically significant. Diversity-based biotic indices derived from both morphological and metabarcoding approaches, reflect the environmental stress gradient (i.e., organic and metal contaminations) in the Kuwait Bay. The lowest values of EcoQS (i.e., bad to poor) are found in the innermost part (i.e., Sulaibikhat Bay and Ras Kazmah), while higher EcoQS values occur in the outer part of the bay. This study constitutes the first attempt to apply the foraminiferal metabarcoding to assess the EcoQS within the Arabian Gulf and presents its advantages compared to the conventional morphological approach.