Search

• Concentrations and diversity of global freshwater MPs vary considerably. • Global warming increased MP concentrations and decreased diversity. • Overall risk rank of freshwater MPs increased under global warming. • Elevated concentrations are the key to increased risk of MPs under global warming. Microplastics present a significant threat to freshwater ecosystems. However, the impact of global warming on their characteristics and associated risks remains uncertain. This study collected 2793 sample sites from literature and datasets to create a new risk assessment and rank methodology, known as the Multi-characteristics Potential Ecological Risk Index (MPERI), which incorporates various microplastic characteristics, such as concentration, size distribution, color, shape, and polymer diversity. Using regression random forest models (RRF), this study predicted that a 10 °C increase would raise microplastic concentration from 12,465.34 ± 68,603.87 to 13,387.17 ± 60,692.96 particles/m3. The percentage of small-size microplastics initially decreased (from 69.10 % to 68.72 %) and then increased (from 68.72 % to 68.78 %), while the diversity of color, shape, and polymer decreased by 0.29 %, 3.24 %, and 0.17 %, respectively. Furthermore, global warming could increase the rank of microplastic risks from high (405.25 ± 528.9) to dangerous (535.37 ± 582.03) based on the MPERI method. Most countries would experience an increase in risk values, with Indonesia and Vietnam transitioning from low to medium risk, and China and Malaysia transitioning from high to dangerous risk. The feature importance assessment of the RRF model indicated that concentration was the most influential variable in determining the change in risk values. While other microplastic characteristics had a lesser impact compared to concentration, they still influenced the risk ranking. This study highlights the role of global warming in shaping microplastic risks. [ABSTRACT FROM AUTHOR]

Thermal infrared (TIR) imagery is normally acquired at coarser pixel resolution than that of shortwave sensors on the same satellite platform. TIR resolution is often not suitable for monitoring crop conditions of fragmented farming lands, e.g., the accurate estimates of evapotranspiration (ET) based on surface energy balance from remote sensing for irrigation water management. Consequently, thermal sharpening techniques have been developed to sharpen TIR imagery to a shortwave band pixel resolution. However, most methods concentrate on the visual effects of the thermal sharpened images, and they treat the pixels as independent samples without considering their spatial context, which can give rise to adverse effects such as artifacts. In this work, a new thermal sharpening method called TS²uRF is proposed. The potential of superpixels (SP) combined with regression random forest (RRF) have been used to augment the spatial resolution of the Landsat 8 TIR (100 m) imagery to their visible (VIS) spatial resolution (30 m). The SP has allowed the contextual information on the land cover to be integrated, and RRF has allowed the relationship between five spectral indices and TIR data to be integrated into a single model. The TIR sharpened images obtained using the TS²uRF were compared with images obtained using the TsHARP, one of the most classic thermal sharpening techniques, evaluating the root-mean-square error (RMSE) and structural similarity index (SSIM) for measuring image quality. In all of the cases evaluated, the RMSE and SSIM of the images sharpened using the TS²uRF method outperform those obtained using TsHARP. In particular, the TS²uRF method has an average error of 1.14 °C (RMSE) lower than TsHARP, regarding SSIM, TS²uRF outperforms TsHARP on average by 0.218. From the visual comparison, it has been shown that the TS²uRF methodology avoids the artifacts that appear in the enhanced images using the TsHARP method. [ABSTRACT FROM AUTHOR]

In this research, a partial least squares (PLS)-based RF with hybrid feature subspace selection is proposed for regression problems. For the problem that average voting strategy of basic RF may decrease method accuracy, PLS is adopted to automatically assign a voting weight to each tree and aggregate the outputs of all trees. To improve feature subspace selection, stratified sampling and embedded feature selection are integrated. First, the variable importance (VI) of each input feature is obtained through embedded feature selection and the features are categorized into two disjointed sets according to VI. During the construction of the trees, stratified sampling is used for feature subspace selection. The effectiveness of PLS aggregation and hybrid feature selection is respectively validated on six regression datasets. The superiority of the proposed RF is demonstrated on historical operation datasets of two power plants through a comparison with five other models. • Partial least square is used to weight each tree of random forest (RF). • An embedded feature selection with stratified sampling is also applied to improve RF. • The variable importance evaluated by RF is used to stratify the features. • The improved RF is applied on UCI and operation datasets of coal-fired boilers. • The results indicate the effectiveness of proposed model for regression problems. [ABSTRACT FROM AUTHOR]

Thermal infrared (TIR) imagery is normally acquired at coarser pixel resolution than that of shortwave sensors on the same satellite platform. TIR resolution is often not suitable for monitoring crop conditions of fragmented farming lands, e.g., the accurate estimates of evapotranspiration (ET) based on surface energy balance from remote sensing for irrigation water management. Consequently, thermal sharpening techniques have been developed to sharpen TIR imagery to a shortwave band pixel resolution. However, most methods concentrate on the visual effects of the thermal sharpened images, and they treat the pixels as independent samples without considering their spatial context, which can give rise to adverse effects such as artifacts. In this work, a new thermal sharpening method called TS2uRF is proposed. The potential of superpixels (SP) combined with regression random forest (RRF) have been used to augment the spatial resolution of the Landsat 8 TIR (100 m) imagery to their visible (VIS) spatial resolution (30 m). The SP has allowed the contextual information on the land cover to be integrated, and RRF has allowed the relationship between five spectral indices and TIR data to be integrated into a single model. The TIR sharpened images obtained using the TS2uRF were compared with images obtained using the TsHARP, one of the most classic thermal sharpening techniques, evaluating the root-mean-square error (RMSE) and structural similarity index (SSIM) for measuring image quality. In all of the cases evaluated, the RMSE and SSIM of the images sharpened using the TS2uRF method outperform those obtained using TsHARP. In particular, the TS2uRF method has an average error of 1.14 °C (RMSE) lower than TsHARP, regarding SSIM, TS2uRF outperforms TsHARP on average by 0.218 . From the visual comparison, it has been shown that the TS2uRF methodology avoids the artifacts that appear in the enhanced images using the TsHARP method.

Random forests are a powerful machine learning tool that capture complex relationships between independent variables and an outcome of interest. Trees built in a random forest are dependent on several hyperparameters, one of the more critical being the node size. The original algorithm of Breiman, controls for node size by limiting the size of the parent node, so that a node cannot be split if it has less than a specified number of observations. We propose that this hyperparameter should instead be defined as the minimum number of observations in each terminal node. The two existing random forest approaches are compared in the regression context based on estimated generalization error, bias-squared, and variance of resulting predictions in a number of simulated datasets. Additionally the two approaches are applied to type 2 diabetes data obtained from the National Health and Nutrition Examination Survey. We have developed a straightforward method for incorporating weights into the random forest analysis of survey data. Our results demonstrate that generalization error under the proposed approach is competitive to that attained from the original random forest approach when data have large random error variability. The R code created from this work is available and includes an illustration.