Evaluation of traditional and machine learning approaches for modeling volatile fatty acid concentrations in anaerobic digestion of sludge: potential and challenges

This study evaluates models for predicting volatile fatty acid (VFA) concentrations in sludge processing, ranging from classical statistical methods (Gaussian and Surge) to diverse machine learning algorithms (MLAs) such as Decision Tree, XGBoost, CatBoost, LightGBM, Multiple linear regression (MLR), Support vector regression (SVR), AdaBoost, and GradientBoosting. Anaerobic bio-methane potential tests were carried out using domestic wastewater treatment primary and secondary sludge. The tests were monitored over 40 days for variations in pH and VFA concentrations under different experimental conditions. The data observed was compared to predictions from the Gaussian and Surge models, and the MLAs. Based on correlation analysis using basic statistics and regression, the Gaussian model appears to be a consistent performer, with high R2 values and low RMSE, favoring precision in forecasting VFA concentrations. The Surge model, on the other hand, albeit having a high R2, has high prediction errors, especially in dynamic VFA concentration settings. Among the MLAs, Decision Tree and XGBoost excel at predicting complicated patterns, albeit with overfitting issues. This study provides insights underlining the need for context-specific considerations when selecting models for accurate VFA forecasts. Real-time data monitoring and collaborative data sharing are required to improve the reliability of VFA prediction models in AD processes, opening the way for breakthroughs in environmental sustainability and bioprocessing applications.

Selecting the optimal gridded climate dataset for Nigeria using advanced time series similarity algorithms

Choosing a suitable gridded climate dataset is a significant challenge in hydro-climatic research, particularly in areas lacking long-term, reliable, and dense records. This study used the most common method (Perkins skill score (PSS)) with two advanced time series similarity algorithms, short time series distance (STS), and cross-correlation distance (CCD), for the first time to evaluate, compare, and rank five gridded climate datasets, namely, Climate Research Unit (CRU), TERRA Climate (TERRA), Climate Prediction Center (CPC), European Reanalysis V.5 (ERA5), and Climatologies at high resolution for Earth's land surface areas (CHELSA), according to their ability to replicate the in situ rainfall and temperature data in Nigeria. The performance of the methods was evaluated by comparing the ranking obtained using compromise programming (CP) based on four statistical criteria in replicating in situ rainfall, maximum temperature, and minimum temperature at 26 locations distributed over Nigeria. Both methods identified CRU as Nigeria's best-gridded climate dataset, followed by CHELSA, TERRA, ERA5, and CPC. The integrated STS values using the group decision-making method for CRU rainfall, maximum and minimum temperatures were 17, 10.1, and 20.8, respectively, while CDD values for those variables were 17.7, 11, and 12.2, respectively. The CP based on conventional statistical metrics supported the results obtained using STS and CCD. CRU's Pbias was between 0.5 and 1; KGE ranged from 0.5 to 0.9; NSE ranged from 0.3 to 0.8; and NRMSE between - 30 and 68.2, which were much better than the other products. The findings establish STS and CCD's ability to evaluate the performance of climate data by avoiding the complex and time-consuming multi-criteria decision algorithms based on multiple statistical metrics.

Smart waste bin monitoring using IoT for sustainable biomedical waste management

Suboptimal management of healthcare waste poses a significant concern that can be effectively tackled by implementing Internet of Things (IoT) solutions to enhance trash monitoring and disposal processes. The potential utilisation of the Internet of Things (IoT) in addressing the requirements associated with biomedical waste management within the Kaduna area was examined. The study included a selection of ten hospitals, chosen based on the criterion of having access to wireless Internet connectivity. The issue of biomedical waste is significant within the healthcare sector since it accounts for a considerable amount of overall waste generation, with estimates ranging from 43.62 to 52.47% across various facilities. Utilisation of (IoT) sensors resulted in the activation of alarms and messages to facilitate the prompt collection of waste. Data collected from these sensors was subjected to analysis to discover patterns and enhance the overall efficiency of waste management practices. The study revealed a positive correlation between the quantity of hospital beds and the daily garbage generated. Notably, hospitals with a higher number of beds were observed to generate a much greater amount of waste per bed. Hazardous waste generated varies by hospital, with one hospital leading in sharps waste (10.98 kgd-1) and chemical waste (21.06 kgd-1). Other hospitals generate considerable amounts of radioactive waste (0.60 kgd-1 and 0.50 kgd-1), pharmaceuticals, and genotoxic waste (16.19 kgd-1), indicating the need for specialised waste management approaches. The study sheds light on the significance of IoT in efficient waste collection and the need for tailored management of hazardous waste.

Adaptation measures under the impacts of climate and land-use/land-cover changes using HSPF model simulation: Application to Gongola river basin, Nigeria

Recently, there is an upsurge in flood emergencies in Nigeria, in which their frequencies and impacts are expected to exacerbate in the future due to land-use/land cover (LULC) and climate change stressors. The separate and combined forces of these stressors on the Gongola river basin is feebly understood and the probable future impacts are not clear. Accordingly, this study uses a process-based watershed modelling approach - the Hydrological Simulation Program FORTRAN (HSPF) (i) to understand the basin's current and future hydrological fluxes and (ii) to quantify the effectiveness of five management options as adaptation measures for the impacts of the stressors. The ensemble means of the three models derived from the Coupled Model Intercomparison Project Phase 5 (CMIP5) are employed for generating future climate scenarios, considering three distinct radiative forcing peculiar to the study area. Also, the historical and future LULC (developed from the hybrid of Cellular Automata and Markov Chain model) are used to produce the LULC scenarios for the basin. The effective calibration, uncertainty and sensitivity analyses are used for optimising the parameters of the model and the validated result implies a plausible model with efficiency of up to 75 %. Consequently, the results of individual impacts of the stressors yield amplification of the peak flows, with more profound impacts from climate stressor than the LULC. Therefore, the climate impact may trigger a marked peak discharge that is 48 % higher as compared to the historical peak flows which are equivalent to 10,000-year flood event. Whilst the combine impacts may further amplify this value by 27 % depending on the scenario. The proposed management interventions such as planned reforestation and reservoir at Dindima should attenuate the disastrous peak discharges by almost 36 %. Furthermore, the land management option should promote the carbon-sequestering project of the Paris agreement ratified by Nigeria. While the reservoir would serve secondary functions of energy production; employment opportunities, aside other social aspects. These measures are therefore expected to mitigate feasibly the negative impacts anticipated from the stressors and the approach can be employed in other river basins in Africa confronted with similar challenges.