Search

This paper presents an automated machine learning framework designed to assist hydrologists in detecting anomalies in time series data generated by sensors in a research watershed in the northeastern United States critical zone. The framework specifically focuses on identifying peak-pattern anomalies, which may arise from sensor malfunctions or natural phenomena. However, the use of classification methods for anomaly detection poses challenges, such as the requirement for labeled data as ground truth and the selection of the most suitable deep learning model for the given task and dataset. To address these challenges, our framework generates labeled datasets by injecting synthetic peak patterns into synthetically generated time series data and incorporates an automated hyperparameter optimization mechanism. This mechanism generates an optimized model instance with the best architectural and training parameters from a pool of five selected models, namely Temporal Convolutional Network (TCN), InceptionTime, MiniRocket, Residual Networks (ResNet), and Long Short-Term Memory (LSTM). The selection is based on the user’s preferences regarding anomaly detection accuracy and computational cost. The framework employs Time-series Generative Adversarial Networks (TimeGAN) as the synthetic dataset generator. The generated model instances are evaluated using a combination of accuracy and computational cost metrics, including training time and memory, during the anomaly detection process. Performance evaluation of the framework was conducted using a dataset from a watershed, demonstrating consistent selection of the most fitting model instance that satisfies the user’s preferences.

ABSTRACTWe examine the interactions, decisions, and evaluations of an interdisciplinary team of researchers tasked with developing an artificial intelligence-based agricultural decision support system that can provide farmers site-specific information about managing nutrients on their land. We answer the following research questions: (1) How does a relational perspective help an interdisciplinary team conceptualize ‘responsibility' in a project that develops precision agriculture (PA)? and (2) What are some lessons for a research team embarking on a similar interdisciplinary technology development project? We show that how RI is materialized in practice within an interdisciplinary research team can produce different understandings of responsibility, notions of measurement of ‘matter,’ and metrics of success. Future interdisciplinary projects should (1) create mechanisms for project members to see how power and privilege are exercised in the design of new technology and (2) harness social sciences as a bridge between natural sciences and engineering for organic and equitable collaborations.

Dengue virus causes a range of inflammatory pathology but understanding critical phases of the infection during human infection has been challenging. Here the author’s present immunotranscriptomic changes during the acute and clearance phases of a dengue virus serotype 2 human challenge model.

Abstract With mounting scientific evidence demonstrating adverse global climate change (GCC) impacts to water quality, water quality policies, such as the Total Maximum Daily Loads (TMDLs) under the U.S. Clean Water Act, have begun accounting for GCC effects in setting nutrient load‐reduction policy targets. These targets generally require nutrient reductions for attaining prescribed water quality standards (WQS) by setting safe levels of nutrient concentrations that curtail potentially harmful cyanobacteria blooms (CyanoHABs). While some governments require WQS to consider climate change, few tools are available to model the complex interactions between climate change and benthic legacy nutrients. We present a novel process‐based integrated assessment model (IAM) that examines the extent to which synergistic relationships between GCC and legacy Phosphorus release could compromise the ability of water quality policies to attain established WQS. The IAM is calibrated for simulating the eutrophic Missisquoi Bay and watershed in Lake Champlain (2001–2050). Water quality impacts of seven P‐reduction scenarios, including the 64.3% reduction specified under the current TMDL, were examined under 17 GCC scenarios. The TMDL WQS of 0.025 mg/L total phosphorus is unlikely to be met by 2035 under the mandated 64.3% reduction for all GCC scenarios. IAM simulations show that the frequency and severity of summer CyanoHABs increased or minimally decreased under most climate and nutrient reduction scenarios. By harnessing IAMs that couple complex process‐based simulation models, the management of water quality in freshwater lakes can become more adaptive through explicit accounting of GCC effects on both the external and internal sources of nutrients.

Understanding and predicting catchment responses to a regional disturbance is difficult because catchments are spatially heterogeneous systems that exhibit unique moderating characteristics. Changes in precipitation composition in the Northeastern U.S. is one prominent example, where reduction in wet and dry deposition is hypothesized to have caused increased dissolved organic carbon (DOC) export from many northern hemisphere forested catchments; however, findings from different locations contradict each other. Using shifts in acid deposition as a test case, we illustrate an iterative “process and pattern” approach to investigate the role of catchment characteristics in modulating the steam DOC response. We use a novel dataset that integrates regional and catchment-scale atmospheric deposition data, catchment characteristics and co-located stream Q and stream chemistry data. We use these data to investigate opportunities and limitations of a pattern-to-process approach where we explore regional patterns of reduced acid deposition, catchment characteristics and stream DOC response and specific soil processes at select locations. For pattern investigation, we quantify long-term trends of flow-adjusted DOC concentrations in stream water, along with wet deposition trends in sulfate, for USGS headwater catchments using Seasonal Kendall tests and then compare trend results to catchment attributes. Our investigation of climatic, topographic, and hydrologic catchment attributes vs. directionality of DOC trends suggests soil depth and catchment connectivity as possible modulating factors for DOC concentrations. This informed our process-to-pattern investigation, in which we experimentally simulated increased and decreased acid deposition on soil cores from catchments of contrasting long-term DOC response [Sleepers River Research Watershed (SRRW) for long-term increases in DOC and the Susquehanna Shale Hills Critical Zone Observatory (SSHCZO) for long-term decreases in DOC]. SRRW soils generally released more DOC than SSHCZO soils and losses into recovery solutions were higher. Scanning electron microscope imaging indicates a significant DOC contribution from destabilizing soil aggregates mostly from hydrologically disconnected landscape positions. Results from this work illustrate the value of an iterative process and pattern approach to understand catchment-scale response to regional disturbance and suggest opportunities for further investigations.

Excessive streambank erosion is a significant source of fine sediments and associated nutrients in many river systems as well as poses risk to infrastructure. Geomorphic change detection using high-resolution topographic data is a useful method for monitoring the extent of bank erosion along river corridors. Recent advances in an unmanned aircraft system (UAS) and structure from motion (SfM) photogrammetry techniques allow acquisition of high-resolution topographic data, which are the methods used in this study. To evaluate the effectiveness of UAS-based photogrammetry for monitoring bank erosion, a fixed-wing UAS was deployed to survey 20 km of river corridors in central Vermont, in the northeastern United States multiple times over a two-year period. Digital elevation models (DEMs) and DEMs of difference allowed quantification of volumetric changes along selected portions of the survey area where notable erosion occurred. Results showed that UAS was capable of collecting high-quality topographic data at fine resolutions even along vegetated river corridors provided that the surveys were conducted in early spring, after snowmelt but prior to summer vegetation growth. Longer term estimates of streambank movements using the UAS showed good comparison to previously collected airborne lidar surveys and allowed reliable quantification of significant geomorphic changes along rivers.

This paper presents the first time series clustering benchmark utilizing all time series datasets currently available in the University of California Riverside (UCR) archive — the state of the art repository of time series data. Specifically, the benchmark examines eight popular clustering methods representing three categories of clustering algorithms (partitional, hierarchical and density-based) and three types of distance measures (Euclidean, dynamic time warping, and shape-based), while adhering to six restrictions on datasets and methods to make the comparison as unbiased as possible. A phased evaluation approach was then designed for summarizing dataset-level assessment metrics and discussing the results. The benchmark study presented can be a useful reference for the research community on its own; and the dataset-level assessment metrics reported may be used for designing evaluation frameworks to answer different research questions.

There is growing environmental psychology and behavior literature with mixed empirical evidence about the influence of public risk perceptions on the adoption of environmentally friendly “green behaviors”. Adoption of stormwater green infrastructure on residential properties, while costlier in the short term compared to conventional greywater infrastructure, plays an important role in the reduction of nutrient loading from non-point sources into freshwater rivers and lakes. In this study, we use Bayesian Belief Networks (BBNs) to analyze a 2015 survey dataset (sample size = 472 respondents) about the adoption of green infrastructure (GSI) in Vermont’s residential areas, most of which are located in either the Lake Champlain Basin or Connecticut River Basin. Eight categories of GSI were investigated: roof diversion, permeable pavement, infiltration trenches, green roofs, rain gardens, constructed wetlands, tree boxes, and others. Using both unsupervised and supervised machine learning algorithms, we used Bayesian Belief Networks to quantify the influence of public risk perceptions on GSI adoption while accounting for a range of demographic and spatial variables. We also compare the effectiveness of the Bayesian Belief Network approach and logistic regression in predicting the pro-environmental behaviors (adoption of GSI). The results show that influencing factors for current adoption differ by the type of GSI. Increased perception of risk from stormwater issues is associated with the adoption of rain gardens and infiltration trenches. Runoff issues are more likely to be considered the governments’ (town, state, and federal agencies) responsibility, whereas lawn erosion is more likely to be considered the residents’ responsibility. When using the same set of variables to predict pro-environmental behaviors (adoption of GSI), the BBN approach produces more accurate predictions compared to logistic regression. The results provide insights for further research on how to encourage residents to take measures for mitigating stormwater issues and stormwater management.

Plug-in hybrid electric vehicles (PHEVs) offer the potential to significantly reduce greenhouse gas emissions, if vehicle consumers are willing to adopt this new technology. Consequently, there is much interest in exploring PHEV market penetration models. In prior work, we developed an agent-based model (ABM) of potential PHEV consumer adoption that incorporated several spatial, social, and media influences to identify nonlinear interactions among potential leverage points that may impact PHEV market penetration. In developing that model, the need for additional data to properly inform both the decision-making rules and agent initialization became apparent. To address these issues, we recently conducted and analyzed an extensive consumer survey; in this paper, we modify the ABM to reflect the survey findings. A unique aspect is a one-to-one correspondence between agents in the model and survey respondents, and thus yielding distributions and cross correlations in agent attributes that accurately reflect the survey population. We also implement a used-PHEV market, and allow agents to purchase new or used compact PHEVs or vehicles of their current type. Based on our prior survey response analysis, our modified model includes a PHEV-technology threshold component, a multinomial logistic prediction of willingness to consider a compact PHEV based on dynamically changing attitudes, and agent-specific delay discounting functions that predict the amount agents are willing to pay up front for greater fuel savings. We thus independently account for agents' discomfort with the new PHEV technology, their desire to drive a more environmentally friendly vehicle, and their willingness to pay a higher sticker price for a PHEV. Results of ten survey-based ABM scenarios are reported with implications for policy-makers and manufacturers. We believe close integration of the design of consumer surveys and the development of ABMs is a key step in developing useful decision-support models; this paper serves as an example of one way to achieve that.

Autism spectrum disorder (ASD) is a neurodevelopmental disorder that can cause significant social, communication, and behavioral challenges. Diagnosis of ASD is complicated and there is an urgent need to identify ASD-associated biomarkers and features to help automate diagnostics and develop predictive ASD models. The present study adopts a novel evolutionary algorithm, the conjunctive clause evolutionary algorithm (CCEA), to select features most significant for distinguishing individuals with and without ASD, and is able to accommodate datasets having a small number of samples with a large number of feature measurements. The dataset is unique and comprises both behavioral and neuroimaging measurements from a total of 28 children from 7 to 14 years old. Potential biomarker candidates identified include brain volume, area, cortical thickness, and mean curvature in specific regions around the cingulate cortex, frontal cortex, and temporal-parietal junction, as well as behavioral features associated with theory of mind. A separate machine learning classifier (i.e., k-nearest neighbors algorithm) was used to validate the CCEA feature selection and for ASD prediction. Study findings demonstrate how machine learning tools might help move the needle on improving diagnostic and predictive models of ASD.

Conversation has been a primary means for the exchange of information since ancient times. Understanding patterns of information flow in conversations is a critical step in assessing and improving communication quality. In this paper, we describe COnversational DYnamics Model (CODYM) analysis, a novel approach for studying patterns of information flow in conversations. CODYMs are Markov Models that capture sequential dependencies in the lengths of speaker turns. The proposed method is automated and scalable, and preserves the privacy of the conversational participants. The primary function of CODYM analysis is to quantify and visualize patterns of information flow, concisely summarized over sequential turns from one or more conversations. Our approach is general and complements existing methods, providing a new tool for use in the analysis of any type of conversation. As an important first application, we demonstrate the model on transcribed conversations between palliative care clinicians and seriously ill patients. These conversations are dynamic and complex, taking place amidst heavy emotions, and include difficult topics such as end-of-life preferences and patient values. We use CODYMs to identify normative patterns of information flow in serious illness conversations, show how these normative patterns change over the course of the conversations, and show how they differ in conversations where the patient does or doesn't audibly express anger or fear. Potential applications of CODYMs range from assessment and training of effective healthcare communication to comparing conversational dynamics across languages, cultures, and contexts with the prospect of identifying universal similarities and unique "fingerprints" of information flow.

Chagas disease, considered a neglected disease by the World Health Organization, is caused by the protozoan parasite Trypanosoma cruzi, and transmitted by >140 triatomine species across the Americas. In Central America, the main vector is Triatoma dimidiata, an opportunistic blood meal feeder inhabiting both domestic and sylvatic ecotopes. Given the diversity of interacting biological agents involved in the epidemiology of Chagas disease, having simultaneous information on the dynamics of the parasite, vector, the gut microbiome of the vector, and the blood meal source would facilitate identifying key biotic factors associated with the risk of T. cruzi transmission. In this study, we developed a RADseq-based analysis pipeline to study mixed-species DNA extracted from T. dimidiata abdomens. To evaluate the efficacy of the method across spatial scales, we used a nested spatial sampling design that spanned from individual villages within Guatemala to major biogeographic regions of Central America. Information from each biotic source was distinguished with bioinformatics tools and used to evaluate the prevalence of T. cruzi infection and predominant Discrete Typing Units (DTUs) in the region, the population genetic structure of T. dimidiata, gut microbial diversity, and the blood meal history. An average of 3.25 million reads per specimen were obtained, with approximately 1% assigned to the parasite, 20% to the vector, 11% to bacteria, and 4% to putative blood meals. Using a total of 6,405 T. cruzi SNPs, we detected nine infected vectors harboring two distinct DTUs: TcI and a second unidentified strain, possibly TcIV. Vector specimens were sufficiently variable for population genomic analyses, with a total of 25,710 T. dimidiata SNPs across all samples that were sufficient to detect geographic genetic structure at both local and regional scales. We observed a diverse microbiotic community, with significantly higher bacterial species richness in infected T. dimidiata abdomens than those that were not infected. Unifrac analysis suggests a common assemblage of bacteria associated with infection, which co-occurs with the typical gut microbial community derived from the local environment. We identified vertebrate blood meals from five T. dimidiata abdomens, including chicken, dog, duck and human; however, additional detection methods would be necessary to confidently identify blood meal sources from most specimens. Overall, our study shows this method is effective for simultaneously generating genetic data on vectors and their associated parasites, along with ecological information on feeding patterns and microbial interactions that may be followed up with complementary approaches such as PCR-based parasite detection, 18S eukaryotic and 16S bacterial barcoding.

In this study we compared the utility of two molecular biology techniques, cloning of the mitochondrial 12S ribosomal RNA gene and hydrolysis probe-based qPCR, to identify blood meal sources of sylvatic Chagas disease insect vectors collected with live-bait mouse traps (also known as Noireau traps). Fourteen T. guasayana were collected from six georeferenced trap locations in the Andean highlands of the department of Chuquisaca, Bolivia.We detected four blood meals sources with the cloning assay: seven samples were positive for human (Homo sapiens), five for chicken (Gallus gallus) and unicolored blackbird (Agelasticus cyanopus), and one for opossum (Monodelphis domestica). Using the qPCR assay we detected chicken (13 vectors), and human (14 vectors) blood meals as well as an additional blood meal source, Canis sp. (4 vectors).We show that cloning of 12S PCR products, which avoids bias associated with developing primers based on a priori knowledge, detected blood meal sources not previously considered and that species-specific qPCR is more sensitive. All samples identified as positive for a specific blood meal source by the cloning assay were also positive by qPCR. However, not all samples positive by qPCR were positive by cloning. We show the power of combining the cloning assay with the highly sensitive hydrolysis probe-based qPCR assay provides a more complete picture of blood meal sources for insect disease vectors.