Impacts of nested forward validation techniques on machine learning and regression waste disposal time series models

Chloride corrosion destabilizes chelation of fresh and aged MSWI fly ash: Mechanism and long-term behavior

Chloride ion (Cl-) contributes to the chelated incineration fly ash (CIFA) destabilization, yet there is limited research available on the effect of exogenous Cl- corrosion. This study conducted 60-day column leaching experiments on fresh and aged CIFA (CIFA-F and CIFA-A), utilizing NaCl solutions at concentrations of 0 wt%, 1 wt%, and 3 wt%. It investigated the leaching behaviors of typical heavy metals (HMs) including lead, chromium, and nickel, associated with the leaching features like contents of calcium and dissolved organic matter (DOM), electrical conductivity, and pH. These leaching features were influenced by Cl- level through buffering and salting-out effects, indirectly affecting HM leaching. HM leaching followed a multi-step mechanism: Initially, HM leaching was primarily controlled by outer-sphere ion exchange and diffusion. As the process transitioned, the presence of Cl- hindered the incorporation of OH-, affecting the formation of secondary minerals like Ca2Al(OH)6(H2O)2Cl. This decreased the net charge and specific surface area, reducing CIFA adsorption capacities towards HMs and DOM. Eventually, large quantities of DOM reacted with HM forming non-adsorptive complexes or colloids. Compared to CIFA-F, the more porous structure in CIFA-A that resulted from carbonation may enhanced Cl- interaction with the internal composition, escalating HM long-term leaching risks. To predict future HM leaching behavior, five machine learning models based on the experimental results were constructed, moving beyond traditional decay models. The multi-output long short-term memory model showed best performance (R²> 0.85, MAE < 5.00 %), confirming its superiority. This study offers microscopic insights into the mechanisms of Cl- corrosion causing CIFA destabilization and advances predictive approaches for HM leaching behaviors.

Prophet time series modeling of waste disposal rates in four North American cities

In this study, three different univariate municipal solid waste (MSW) disposal rate forecast models (SARIMA, Holt-Winters, Prophet) were examined using different testing periods in four North American cities with different socioeconomic conditions. A review of the literature suggests that the selected models are able to handle seasonality in a time series; however, their ability to handle outliers is not well understood. The Prophet model generally outperformed the Holt-Winters model and the SARIMA model. The MAPE and R2 of the Prophet model during pre-COVID-19 were 4.3-22.2% and 0.71-0.93, respectively. All three models showed satisfactory predictive results, especially during the pre-COVID-19 testing period. COVID-19 lockdowns and the associated regulatory measures appear to have affected MSW disposal behaviors, and all the univariate models failed to fully capture the abrupt changes in waste disposal behaviors. Modeling errors were largely attributed to data noise in seasonality and the unprecedented event of COVID-19 lockdowns. Overall, the modeling errors of the Prophet model were evenly distributed, with minimum modeling biases. The Prophet model also appeared to be versatile and successfully captured MSW disposal rates from 3000 to 39,000 tons/month. The study highlights the potential benefits of the use of univariate models in waste forecast.

Minimizing artifact-induced false-alarms for seizure detection in wearable EEG devices with gradient-boosted tree classifiers

Electroencephalography (EEG) is widely used to monitor epileptic seizures, and standard clinical practice consists of monitoring patients in dedicated epilepsy monitoring units via video surveillance and cumbersome EEG caps. Such a setting is not compatible with long-term tracking under typical living conditions, thereby motivating the development of unobtrusive wearable solutions. However, wearable EEG devices present the challenges of fewer channels, restricted computational capabilities, and lower signal-to-noise ratio. Moreover, artifacts presenting morphological similarities to seizures act as major noise sources and can be misinterpreted as seizures. This paper presents a combined seizure and artifacts detection framework targeting wearable EEG devices based on Gradient Boosted Trees. The seizure detector achieves nearly zero false alarms with average sensitivity values of [Formula: see text] for 182 seizures from the CHB-MIT dataset and [Formula: see text] for 25 seizures from the private dataset with no preliminary artifact detection or removal. The artifact detector achieves a state-of-the-art accuracy of [Formula: see text] (on the TUH-EEG Artifact Corpus dataset). Integrating artifact and seizure detection significantly reduces false alarms-up to [Formula: see text] compared to standalone seizure detection. Optimized for a Parallel Ultra-Low Power platform, these algorithms enable extended monitoring with a battery lifespan reaching 300 h. These findings highlight the benefits of integrating artifact detection in wearable epilepsy monitoring devices to limit the number of false positives.

Prediction of photovoltaic waste generation in Canada using regression-based model

The global surge in photovoltaic (PV) installations and the resulting increase in PV waste are a growing concern. The aims of this study include predicting the volume of photovoltaic waste in Canada. The forecasting of solar waste volume employed linear regression, 2nd order polynomial regression, and power regression models. The study's results indicate that Canada is on the verge of facing challenges related to the end-of-life treatment of photovoltaic modules in the coming years due to the significant growth in PV capacity over recent decades. According to the analysis, for early loss, the PV waste volume in 2045 could range from 180,000 MT to 270,000 MT, and for regular loss, it could range from 160,000 MT to 180,000 MT. This research is anticipated to assist relevant government agencies in assessing the prospective volume of PV waste to establish a sustainable and resilient PV waste management plan for Canada. These findings may shed light on the feasibility of a circular economy and advocate for the involvement of all stakeholders in a carefully coordinated strategy to mitigate potential environmental impacts and optimize resource utilization efficiency.

A cross-jurisdictional comparison on residential waste collection rates during earlier waves of COVID-19

There is currently a lack of studies on residential waste collection during COVID-19 in North America. SARIMA models were developed to predict residential waste collection rates (RWCR) across four North American jurisdictions before and during the pandemic. Unlike waste disposal rates, RWCR is relatively less sensitive to the changes in COVID-19 regulatory policies and administrative measures, making RWCR more appropriate for cross-jurisdictional comparisons. It is hypothesized that the use of RWCR in forecasting models will help us to better understand the residential waste generation behaviors in North America. Both SARIMA models performed satisfactorily in predicting Regina's RWCR. The SARIMA DCV model's performance is noticeably better during COVID-19, with a 15.7% lower RMSE than that of the benchmark model (SARIMA BCV). The skewness of overprediction ratios was noticeably different between jurisdictions, and modeling errors were generally lower in less populated cities. Conflicting behavioral changes might have altered the residential waste generation characteristics and recycling behaviors differently across the jurisdictions. Overall, SARIMA DCV performed better in the Canadian jurisdiction than in U.S. jurisdictions, likely due to the model's bias on a less variable input dataset. The use of RWCR in forecasting models helps us to better understand the residential waste generation behaviors in North America and better prepare us for a future global pandemic.