Assessing the effectiveness of a residential-scale detention tank operated in a multi-objective approach using SWMM.

The volume capture ratio of annual rainfall (VCRAR) of low-impact development measures is significantly influenced by its operating characteristics, particularly for residential stormwater detention tanks (SWDTs). The multi-objective operation strategy of SWDTs, encompassing toilet flushing (TF), green space irrigation (GSI), combined TF and GSI (TF-GSI), and peak flow reduction (PFR) rate, were compared using a case study in Beijing based on the stormwater management model. The findings indicate that the VCRAR for TF, GSI, and TF-GSI rainwater harvesting targets was 89.05, 77.16, and 91.21%, respectively. The operating scheme and return periods have a significant impact on the PFR rate's effectiveness. When the return period was lower than 10 years, the SWDT does not reach its maximum storage capacity, and the PFR rate was increased with increasing the return period: the PFR rate was 71.47% when the design return period was 10 years. It will also produce the phenomena of water inrush, and the overflow volume will grow rapidly when the SWDT reaches its maximum storage capacity. Hence, the operation of SWDTs may be integrated with real-time control to optimize the VCRAR for rainwater reuse and flood migration, thereby enhancing the volume utilization efficiency of SWDTs.

Characteristics of thermal pollution from stormwater runoff from impermeable/permeable pavement surfaces via a lab-scale experiment.

Thermal pollution from stormwater runoff has been the focus of many studies in recent years due to its potential harm to aquatic microorganisms. However, there were few studies on the thermal pollution caused by stormwater runoff from various types of urban pavement surfaces. A lab-scale experiment was conducted to compare the thermal load of stormwater runoff from impermeable and permeable pavements and the influencing factors were investigated. The experimental findings demonstrated that the rainfall return period and initial temperature of various pavement surfaces significantly impacted the thermal load. The stormwater runoff absorbed more heat as the initial temperature, and rainfall return period increased. The difference of the thermal load of stormwater runoff between permeable brick pavement (PBP) and the impermeable asphalt pavement (IAP) increased from 305.26 to 436.70 kJ/m2, when the initial surface temperature rose from 35 to 47 °C. The average runoff temperature decreased by 1.39-1.90 °C for PBP compared to the IAP, with an increase in surface temperature from 35 to 47 °C. Under the various initial surface temperatures, the mean temperature of the infiltration effluent from the PBP was 3.12-4.20 °C lower than the average temperature of stormwater runoff from the surface layer. Therefore, a PBP can effectively alleviate thermal pollution from stormwater runoff and safeguard the receiving waters' quality.

Development and validation of an interpretable deep learning framework for Alzheimer's disease classification.

Alzheimer's disease is the primary cause of dementia worldwide, with an increasing morbidity burden that may outstrip diagnosis and management capacity as the population ages. Current methods integrate patient history, neuropsychological testing and MRI to identify likely cases, yet effective practices remain variably applied and lacking in sensitivity and specificity. Here we report an interpretable deep learning strategy that delineates unique Alzheimer's disease signatures from multimodal inputs of MRI, age, gender, and Mini-Mental State Examination score. Our framework linked a fully convolutional network, which constructs high resolution maps of disease probability from local brain structure to a multilayer perceptron and generates precise, intuitive visualization of individual Alzheimer's disease risk en route to accurate diagnosis. The model was trained using clinically diagnosed Alzheimer's disease and cognitively normal subjects from the Alzheimer's Disease Neuroimaging Initiative (ADNI) dataset (n = 417) and validated on three independent cohorts: the Australian Imaging, Biomarker and Lifestyle Flagship Study of Ageing (AIBL) (n = 382), the Framingham Heart Study (n = 102), and the National Alzheimer's Coordinating Center (NACC) (n = 582). Performance of the model that used the multimodal inputs was consistent across datasets, with mean area under curve values of 0.996, 0.974, 0.876 and 0.954 for the ADNI study, AIBL, Framingham Heart Study and NACC datasets, respectively. Moreover, our approach exceeded the diagnostic performance of a multi-institutional team of practicing neurologists (n = 11), and high-risk cerebral regions predicted by the model closely tracked post-mortem histopathological findings. This framework provides a clinically adaptable strategy for using routinely available imaging techniques such as MRI to generate nuanced neuroimaging signatures for Alzheimer's disease diagnosis, as well as a generalizable approach for linking deep learning to pathophysiological processes in human disease.

Estimation of Size and Contact Angle of Evaporating Sessile Liquid Drops Using Texture Analysis.

Size and contact angle of liquid drops are fundamental parameters in interfacial science. Accurate estimation of these parameters can provide objective information regarding several properties of the contacting surface. We leveraged principles of texture analysis to estimate the contact angle and the drop diameter from videos of evaporating sessile liquid drops deposited on solid surfaces. Specifically, we used a Harris corner detector to locate the corners and dynamically estimate the changing size and a Gabor wavelet-based approach to estimate the varying contact angle of the evaporating sessile drop. We demonstrated the ability of our approach to accurately estimate size and contact angles of drops deposited on a hydrophilic glass slide and on a paraffin film representing a hydrophobic surface. We also estimated the contact angle and size of drops deposited on horizontal and tilted surfaces to generate symmetric and asymmetric drop shapes, respectively. A software application that has the ability to analyze videos of sessile liquid drops as inputs is provided, and this tool can generate plots of the estimated contact angle and the drop diameter as a function of frame number.

AI-based differential diagnosis of dementia etiologies on multimodal data.

Differential diagnosis of dementia remains a challenge in neurology due to symptom overlap across etiologies, yet it is crucial for formulating early, personalized management strategies. Here, we present an AI model that harnesses a broad array of data, including demographics, individual and family medical history, medication use, neuropsychological assessments, functional evaluations, and multimodal neuroimaging, to identify the etiologies contributing to dementia in individuals. The study, drawing on 51,269 participants across 9 independent, geographically diverse datasets, facilitated the identification of 10 distinct dementia etiologies. It aligns diagnoses with similar management strategies, ensuring robust predictions even with incomplete data. Our model achieved a micro-averaged area under the receiver operating characteristic curve (AUROC) of 0.94 in classifying individuals with normal cognition, mild cognitive impairment and dementia. Also, the micro-averaged AUROC was 0.96 in differentiating the dementia etiologies. Our model demonstrated proficiency in addressing mixed dementia cases, with a mean AUROC of 0.78 for two co-occurring pathologies. In a randomly selected subset of 100 cases, the AUROC of neurologist assessments augmented by our AI model exceeded neurologist-only evaluations by 26.25%. Furthermore, our model predictions aligned with biomarker evidence and its associations with different proteinopathies were substantiated through postmortem findings. Our framework has the potential to be integrated as a screening tool for dementia in various clinical settings and drug trials, with promising implications for person-level management.

Interpretable Machine Learning on Metabolomics Data Reveals Biomarkers for Parkinson's Disease.

The use of machine learning (ML) with metabolomics provides opportunities for the early diagnosis of disease. However, the accuracy of ML and extent of information obtained from metabolomics can be limited owing to challenges associated with interpreting disease prediction models and analyzing many chemical features with abundances that are correlated and "noisy". Here, we report an interpretable neural network (NN) framework to accurately predict disease and identify significant biomarkers using whole metabolomics data sets without a priori feature selection. The performance of the NN approach for predicting Parkinson's disease (PD) from blood plasma metabolomics data is significantly higher than other ML methods with a mean area under the curve of >0.995. PD-specific markers that predate clinical PD diagnosis and contribute significantly to early disease prediction were identified including an exogenous polyfluoroalkyl substance. It is anticipated that this accurate and interpretable NN-based approach can improve diagnostic performance for many diseases using metabolomics and other untargeted 'omics methods.

Fusion of Low-Level Descriptors of Digital Voice Recordings for Dementia Assessment.

Digital voice recordings can offer affordable, accessible ways to evaluate behavior and function. We assessed how combining different low-level voice descriptors can evaluate cognitive status. Using voice recordings from neuropsychological exams at the Framingham Heart Study, we developed a machine learning framework fusing spectral, prosodic, and sound quality measures early in the training cycle. The model's area under the receiver operating characteristic curve was 0.832 (±0.034) in differentiating persons with dementia from those who had normal cognition. This offers a data-driven framework for analyzing minimally processed voice recordings for cognitive assessment, highlighting the value of digital technologies in disease detection and intervention.

Effect of pig manure-derived sulfadiazine on species distribution and bioactivities of soil ammonia-oxidizing microorganisms after fertilization.

To evaluate the effect of pig manure-derived sulfadiazine (SDZ) on the species distribution and bioactivities of ammonia-oxidizing microorganisms (AOMs), ammonia-oxidizing bacteria (AOB), ammonia-oxidizing archaea (AOA) and complete ammonia oxidizer (comammox) within the soil were investigated pre- and post-fertilization. Kinetic modeling and linear regression results demonstrated that the DT50 value of different SDZ fractions under initial SDZ concentrations of 50 and 100 mg·kg-1 exhibited the following trend: total SDZ>CaCl2-extractable SDZ>MeOH-extractable SDZ, whereas their inhibiting effect on AOMs showed an opposite trend. qPCR analysis suggested that comammox was the predominant ammonia oxidizer in soils regardless of SDZ addition, accounting for as much as 77.2-94.7% of the total amoA, followed by AOA (5.3-22.5%), whereas AOB (<0.5%) was the lowest. The SDZ exhibited a significant effect on the AOM abundance. Specifically, SDZ exerted the highest inhibitory effect on comammox growth, followed by AOA, whereas negligible for AOB. The community diversity of AOMs within the pig manure-fertilized soils was affected by SDZ, and AOA Nitrososphaera cluster 3 played a key role in potential ammonia oxidation capacity (PAO) maintenance. This study provides new insights into the inhibition mechanisms of pig manure-derived antibiotics on AOMs within the fertilized soil.

Multimodal deep learning for Alzheimer's disease dementia assessment.

Worldwide, there are nearly 10 million new cases of dementia annually, of which Alzheimer's disease (AD) is the most common. New measures are needed to improve the diagnosis of individuals with cognitive impairment due to various etiologies. Here, we report a deep learning framework that accomplishes multiple diagnostic steps in successive fashion to identify persons with normal cognition (NC), mild cognitive impairment (MCI), AD, and non-AD dementias (nADD). We demonstrate a range of models capable of accepting flexible combinations of routinely collected clinical information, including demographics, medical history, neuropsychological testing, neuroimaging, and functional assessments. We then show that these frameworks compare favorably with the diagnostic accuracy of practicing neurologists and neuroradiologists. Lastly, we apply interpretability methods in computer vision to show that disease-specific patterns detected by our models track distinct patterns of degenerative changes throughout the brain and correspond closely with the presence of neuropathological lesions on autopsy. Our work demonstrates methodologies for validating computational predictions with established standards of medical diagnosis.

Detection of dementia on voice recordings using deep learning: a Framingham Heart Study.

BACKGROUND: Identification of reliable, affordable, and easy-to-use strategies for detection of dementia is sorely needed. Digital technologies, such as individual voice recordings, offer an attractive modality to assess cognition but methods that could automatically analyze such data are not readily available. METHODS AND FINDINGS: We used 1264 voice recordings of neuropsychological examinations administered to participants from the Framingham Heart Study (FHS), a community-based longitudinal observational study. The recordings were 73 min in duration, on average, and contained at least two speakers (participant and examiner). Of the total voice recordings, 483 were of participants with normal cognition (NC), 451 recordings were of participants with mild cognitive impairment (MCI), and 330 were of participants with dementia (DE). We developed two deep learning models (a two-level long short-term memory (LSTM) network and a convolutional neural network (CNN)), which used the audio recordings to classify if the recording included a participant with only NC or only DE and to differentiate between recordings corresponding to those that had DE from those who did not have DE (i.e., NDE (NC+MCI)). Based on 5-fold cross-validation, the LSTM model achieved a mean (±std) area under the receiver operating characteristic curve (AUC) of 0.740 ± 0.017, mean balanced accuracy of 0.647 ± 0.027, and mean weighted F1 score of 0.596 ± 0.047 in classifying cases with DE from those with NC. The CNN model achieved a mean AUC of 0.805 ± 0.027, mean balanced accuracy of 0.743 ± 0.015, and mean weighted F1 score of 0.742 ± 0.033 in classifying cases with DE from those with NC. For the task related to the classification of participants with DE from NDE, the LSTM model achieved a mean AUC of 0.734 ± 0.014, mean balanced accuracy of 0.675 ± 0.013, and mean weighted F1 score of 0.671 ± 0.015. The CNN model achieved a mean AUC of 0.746 ± 0.021, mean balanced accuracy of 0.652 ± 0.020, and mean weighted F1 score of 0.635 ± 0.031 in classifying cases with DE from those who were NDE. CONCLUSION: This proof-of-concept study demonstrates that automated deep learning-driven processing of audio recordings of neuropsychological testing performed on individuals recruited within a community cohort setting can facilitate dementia screening.

Enhancing magnetic resonance imaging-driven Alzheimer's disease classification performance using generative adversarial learning.

BACKGROUND: Generative adversarial networks (GAN) can produce images of improved quality but their ability to augment image-based classification is not fully explored. We evaluated if a modified GAN can learn from magnetic resonance imaging (MRI) scans of multiple magnetic field strengths to enhance Alzheimer's disease (AD) classification performance. METHODS: T1-weighted brain MRI scans from 151 participants of the Alzheimer's Disease Neuroimaging Initiative (ADNI), who underwent both 1.5-Tesla (1.5-T) and 3-Tesla imaging at the same time were selected to construct a GAN model. This model was trained along with a three-dimensional fully convolutional network (FCN) using the generated images (3T*) as inputs to predict AD status. Quality of the generated images was evaluated using signal to noise ratio (SNR), Blind/Referenceless Image Spatial Quality Evaluator (BRISQUE) and Natural Image Quality Evaluator (NIQE). Cases from the Australian Imaging, Biomarker & Lifestyle Flagship Study of Ageing (AIBL, n = 107) and the National Alzheimer's Coordinating Center (NACC, n = 565) were used for model validation. RESULTS: The 3T*-based FCN classifier performed better than the FCN model trained using the 1.5-T scans. Specifically, the mean area under curve increased from 0.907 to 0.932, from 0.934 to 0.940, and from 0.870 to 0.907 on the ADNI test, AIBL, and NACC datasets, respectively. Additionally, we found that the mean quality of the generated (3T*) images was consistently higher than the 1.5-T images, as measured using SNR, BRISQUE, and NIQE on the validation datasets. CONCLUSION: This study demonstrates a proof of principle that GAN frameworks can be constructed to augment AD classification performance and improve image quality.

Development, current state and future trends of sludge management in China: Based on exploratory data and CO2-equivaient emissions analysis.

This study statistically reported the current state of sludge treatment/disposal in China from the aspects of sources, technical routes, geographical distribution, and development by using observational data after 1978. By the end of 2019, 5476 municipal wastewater treatment plants were operating in China, leading to an annual sludge productivity of 39.04 million tons (80% water content). Overall, 29.3% of the sludge in China was disposed via land application, followed by incineration (26.7%) and sanitary landfills (20.1%). Incineration, compost, thermal hydrolysis and anerobic digestion were the mainstream technologies for sludge treatment in China, with capacities of 27,122, 11,250, 8342 and 6944 t/d in 2019, respectively. Incineration and drying were preferentially constructed in East China. In contrast, sludge compost was most frequently used in Northeast China (46.5%), East China (22.4%) and Central China (12.8%), while anaerobic digestion in East China, North China and Central China. The capacities of sludge facilities exhibited a sharp increase in 2009-2019, with an overall greenhouse gas emissions in China in 2019 reached 108.18 × 108 kg CO2-equivaient emissions, and the four main technical routes contributed as: incineration (45.11%) > sanitary landfills (23.04%) > land utilization (17.64%) > building materials (14.21%). Challenges and existing problems of sludge disposal in China, including high CO2 emissions, unbalanced regional development, low stabilization and land utilization levels, were discussed. Finally, suggestions regarding potential technical and administrative measures in China, and sustainable sludge management for developing countries, were also given.

Quantifying the nativeness of antibody sequences using long short-term memory networks.

Antibodies often undergo substantial engineering en route to the generation of a therapeutic candidate with good developability properties. Characterization of antibody libraries has shown that retaining native-like sequence improves the overall quality of the library. Motivated by recent advances in deep learning, we developed a bi-directional long short-term memory (LSTM) network model to make use of the large amount of available antibody sequence information, and use this model to quantify the nativeness of antibody sequences. The model scores sequences for their similarity to naturally occurring antibodies, which can be used as a consideration during design and engineering of libraries. We demonstrate the performance of this approach by training a model on human antibody sequences and show that our method outperforms other approaches at distinguishing human antibodies from those of other species. We show the applicability of this method for the evaluation of synthesized antibody libraries and humanization of mouse antibodies.

Effect of hydraulic retention time on deterioration/restarting of sludge anaerobic digestion: Extracellular polymeric substances and microbial response.

In this study, the transformation of the sludge-related extracellular polymeric substances (EPS) during mesophilic anaerobic digestion was characterized to assess the effect of hydraulic retention time (HRT) on reactor deterioration/restarting. Experimental HRT variations from 20 to 15 and 10d was implemented for deterioration, and from 10 to 20d for restarting. Long-term digestion at the lowest HRT (10d) resulted in significant accumulation of hydrolyzed hydrophobic materials and volatile fatty acids in the supernatants. Moreover, less efficient hydrolysis of sludge EPS, especially of proteins related substances which contributed to the deterioration of digester. Aceticlastic species of Methanosaetaceae decreased from 36.3% to 27.6% with decreasing HRT (20-10d), while hydrogenotrophic methanogens (Methanomicrobiales and Methanobacteriales) increased from 30.4% to 38.3%. Proteins and soluble microbial byproducts related fluorophores in feed sludge for the anaerobic digester changed insignificantly at high HRT, whereas the fluorescent intensity of fulvic acid-like components declined sharply once the digestion deteriorated.

Combined effects of graphene oxide and Cd on the photosynthetic capacity and survival of Microcystis aeruginosa.

In this work, the combined effects of graphene oxide (GO) and Cd(2+) solution on Microcystis aeruginosa were investigated. Chlorophyll fluorescence parameters were measured by a pulse-amplitude modulated fluorometer. GO at low concentrations exhibited no significant toxicity. The presence of GO at low concentrations significantly enhanced Cd(2+) toxicity as the 96 h half maximal effective concentration of the Cd(2+) reduced from 0.51 ± 0.01 to 0.474 ± 0.01 mg/L. However, concentrations of GO above 5mg/L did not significantly increase the toxicity of the Cd(2+)/GO system. Observations through scanning and transmission electron microscopy revealed that GO, with Cd(2+), easily attached to and entered into the algae. Reactive oxygen species and malondialdehyde were measured to explain the toxicity mechanism. The photosynthetic parameters were useful in measuring the combined toxicity of the nanoparticles and heavy metals.

The impact of changes in source water quality on trihalomethane and haloacetonitrile formation in chlorinated drinking water.

This study examined the formation of disinfection by-products (DBPs), including nitrogenous DBPs, haloacetonitriles (HANs), and carbonaceous DBPs, trihalomethanes (THMs), upon chlorination of water samples collected from a conventional Chinese surface water treatment plant (i.e. applying coagulation, sedimentation, and filtration). Reductions in the average concentrations (and range, shown in brackets) of dissolved organic carbon (DOC) and dissolved organic nitrogen (DON) from 4.8 (3.0-7.3) µg/L and 0.52 (0.20-0.81) µg/L in 2010 to 2.4 (1.4-3.7) µg/L and 0.17 (0.11-0.31) µg/L in 2012, respectively, led to a decrease in HANs and THMs from 5.3 and 28.5 µg/L initially to 0.85 and 8.2 µg/L, as average concentrations, respectively. The bromide concentration in the source water also decreased from 2010 to 2012, but the bromine incorporation factor (BIF) for the THMs did not change significantly; however, for HAN the BIFs increased because the reduction in DON was higher than that of bromide. There was good linear relationship between DOC and THM concentrations, but not between DON and HANs.

Effects of dissolved oxygen on extracellular enzymes activities and transformation of carbon sources from plant biomass: implications for denitrification in constructed wetlands.

Dissolved oxygen (DO) concentrations have often been shown to be important to decomposition rates of plant litter and thus may be a key factor in determining the supply of dissolved organic carbon (DOC) and carbon-dependent denitrification in wetlands. During the 2 months operation, DOC accumulation in anaerobic condition was superior to aerobic condition due to higher activities of hydrolase enzymes and lower hydrolysates converted to gaseous C. Also, much higher denitrification rates were observed in wetland when using anaerobic litter leachate as the carbon source, and the available carbon source (ACS) could be used as a good predictor of denitrification rate in wetland. According to the results of this study, extracellular enzymes activities (EEAs) in wetland would change as a short-term consequence of DO. This may alter balance of litter carbon flux and the characteristics of DOC, which may, in turn, have multiple effects on denitrification in wetlands.