Complexity is costly: a meta‐analysis of parametric and non‐parametric methods for short‐term population forecasting

Short‐term forecasts based on time series of counts or survey data are widely used in population biology to provide advice concerning the management, harvest and conservation of natural populations. A common approach to produce these forecasts uses time‐series models, of different types, fit to time series of counts. Similar time‐series models are used in many other disciplines, however relative to the data available in these other disciplines, population data are often unusually short and noisy and models that perform well for data from other disciplines may not be appropriate for population data. In order to study the performance of time‐series forecasting models for natural animal population data, we assembled 2379 time series of vertebrate population indices from actual surveys. Our data were comprised of three vastly different types: highly variable (marine fish productivity), strongly cyclic (adult salmon counts), and small variance but long‐memory (bird and mammal counts). We tested the predictive performance of 49 different forecasting models grouped into three broad classes: autoregressive time‐series models, non‐linear regression‐type models and non‐parametric time‐series models. Low‐dimensional parametric autoregressive models gave the most accurate forecasts across a wide range of taxa; the most accurate model was one that simply treated the most recent observation as the forecast. More complex parametric and non‐parametric models performed worse, except when applied to highly cyclic species. Across taxa, certain life history characteristics were correlated with lower forecast error; specifically, we found that better forecasts were correlated with attributes of slow growing species: large maximum age and size for fishes and high trophic level for birds. Synthesis Evaluating the data support for multiple plausible models has been an integral focus of many ecological analyses. However, the most commonly used tools to quantify support have weighted models’ hindcasting and forecasting abilities. For many applications, predicting the past may be of little interest. Concentrating only on the future predictive performance of time series models, we performed a forecasting competition among many different kinds of statistical models, applying each to many different kinds of vertebrate time series of population abundance. Low‐dimensional (simple) models performed well overall, but more complex models did slightly better when applied to time series of cyclic species (e.g. salmon).     

基于植保大数据的病虫害移动智能采集新设备

为提高农作物重大病虫害发生信息自动化、智能化采集能力,全面提升监测预警水平,笔者基于大数据、人工智能和深度学习技术,研发了一款农作物病虫害移动智能采集设备——智宝,主要实现了3个方面的功能:一是病虫害发生信息自动采集上报.通过该产品进行人工拍照,可实现对田间农作物重大病虫害发生图像、发生位置、发生数量、微环境因子等数据的实时采集和上报.二是自动识别计数.基于植保大数据与人工智能技术,通过构建病虫害自动识别系统,可实现重大病虫害精准识别与分析,只要拍摄照片,即可快速、精确地识别病虫害种类,并自动计数、上报到指定的测报系统.三是自动分析判别分级.针对拍摄采集上报的重大病虫害发生信息,系统可在自动识别和计数的基础上,进一步对病虫害发生严重程度进行智能判别分级,甚至根据相关预测模型,对病虫害的发生趋势进行辅助分析预测,提出预测建议.通过2016—2019年组织多地植保机构进行试验改进,该技术产品日趋成熟,有望在未来的农作物病虫害发生信息采集和预测预报工作中推广使用.     

Fast and accurate influenza forecasting in the United States with Inferno

Infectious disease forecasting is an emerging field and has the potential to improve public health through anticipatory resource allocation, situational awareness, and mitigation planning. By way of exploring and operationalizing disease forecasting, the U.S. Centers for Disease Control and Prevention (CDC) has hosted FluSight since the 2013/14 flu season, an annual flu forecasting challenge. Since FluSight’s onset, forecasters have developed and improved forecasting models in an effort to provide more timely, reliable, and accurate information about the likely progression of the outbreak. While improving the predictive performance of these forecasting models is often the primary objective, it is also important for a forecasting model to run quickly, facilitating further model development and improvement while providing flexibility when deployed in a real-time setting. In this vein I introduce Inferno, a fast and accurate flu forecasting model inspired by Dante, the top performing model in the 2018/19 FluSight challenge. When pseudoprospectively compared to all models that participated in FluSight 2018/19, Inferno would have placed 2nd in the national and regional challenge as well as the state challenge, behind only Dante. Inferno, however, runs in minutes and is trivially parallelizable, while Dante takes hours to run, representing a significant operational improvement with minimal impact to performance. Forecasting challenges like FluSight should continue to monitor and evaluate how they can be modified and expanded to incentivize the development of forecasting models that benefit public health.     

The right time,the right place: will targeting human cancer-associated mutations to the mouse provide the perfect preclinical model?

Over the past 10 years the realisation that genetic mouse models of cancer may play a key role in preclinical drug development has gained strong momentum. Moreover sequencing studies of human tumours have provided key insights into the mutational complexity of epithelial cancer, unleashing important clues for researchers to generate accurate genetically engineered mouse (GEM) models of cancer. Thus by targeting multiple cancer associated human mutations to the appropriate murine epithelia, mice develop tumours that more closely recapitulate the human disease. As a number of excellent models now exist, the next 5-10 years will ascertain whether these models will predict response of human cancer to intervention. If so they might become the 'gold standard' where all drugs are required to be tested in mouse models of disease before proceeding into the patient. However, although this principle is very attractive, it is relatively untested and here, using examples of prevalent human cancers, we will review the latest data on preclinical GEM studies and comment on what challenges are left to overcome.     

Probabilistic seasonal dengue forecasting in Vietnam: A modelling study using superensembles

BackgroundWith enough advanced notice, dengue outbreaks can be mitigated. As a climate-sensitive disease, environmental conditions and past patterns of dengue can be used to make predictions about future outbreak risk. These predictions improve public health planning and decision-making to ultimately reduce the burden of disease. Past approaches to dengue forecasting have used seasonal climate forecasts, but the predictive ability of a system using different lead times in a year-round prediction system has been seldom explored. Moreover, the transition from theoretical to operational systems integrated with disease control activities is rare.Methods and findingsWe introduce an operational seasonal dengue forecasting system for Vietnam where Earth observations, seasonal climate forecasts, and lagged dengue cases are used to drive a superensemble of probabilistic dengue models to predict dengue risk up to 6 months ahead. Bayesian spatiotemporal models were fit to 19 years (2002–2020) of dengue data at the province level across Vietnam. A superensemble of these models then makes probabilistic predictions of dengue incidence at various future time points aligned with key Vietnamese decision and planning deadlines. We demonstrate that the superensemble generates more accurate predictions of dengue incidence than the individual models it incorporates across a suite of time horizons and transmission settings. Using historical data, the superensemble made slightly more accurate predictions (continuous rank probability score [CRPS] = 66.8, 95% CI 60.6–148.0) than a baseline model which forecasts the same incidence rate every month (CRPS = 79.4, 95% CI 78.5–80.5) at lead times of 1 to 3 months, albeit with larger uncertainty. The outbreak detection capability of the superensemble was considerably larger (69%) than that of the baseline model (54.5%). Predictions were most accurate in southern Vietnam, an area that experiences semi-regular seasonal dengue transmission. The system also demonstrated added value across multiple areas compared to previous practice of not using a forecast. We use the system to make a prospective prediction for dengue incidence in Vietnam for the period May to October 2020. Prospective predictions made with the superensemble were slightly more accurate (CRPS = 110, 95% CI 102–575) than those made with the baseline model (CRPS = 125, 95% CI 120–168) but had larger uncertainty. Finally, we propose a framework for the evaluation of probabilistic predictions. Despite the demonstrated value of our forecasting system, the approach is limited by the consistency of the dengue case data, as well as the lack of publicly available, continuous, and long-term data sets on mosquito control efforts and serotype-specific case data.ConclusionsThis study shows that by combining detailed Earth observation data, seasonal climate forecasts, and state-of-the-art models, dengue outbreaks can be predicted across a broad range of settings, with enough lead time to meaningfully inform dengue control. While our system omits some important variables not currently available at a subnational scale, the majority of past outbreaks could be predicted up to 3 months ahead. Over the next 2 years, the system will be prospectively evaluated and, if successful, potentially extended to other areas and other climate-sensitive disease systems.     

Recent developments in monitoring and modelling airborne pollen,a review

Abstract

Public awareness of the rising importance of allergies and other respiratory diseases has led to increased scientific effort to accurately and rapidly monitor and predict pollen, fungal spores and other bioaerosols in our atmosphere. An important driving force for the increased social and scientific concern is the realisation that climate change will increasingly have an impact on worldwide bioaerosol distributions and subsequent human health. In this review we examine new developments in monitoring of atmospheric pollen as well as observation and source-orientated modelling techniques. The results of a Scopus® search for scientific publications conducted with the terms ‘Pollen allergy’ and ‘Pollen forecast’ included in the title, abstract or keywords show that the number of such articles published has increased year on year. The 12 most important allergenic pollen taxa in Europe as defined by COST Action ES0603 were ranked in terms of the most ‘popular’ for model-based forecasting and for forecasting method used. Betula, Poaceae and Ambrosia are the most forecast taxa. Traditional regression and phenological models (including temperature sum and chilling models) are the most used modelling methods, but it is notable that there are a large number of new modelling techniques being explored. In particular, it appears that Machine Learning techniques have become more popular and led to better results than more traditional observation-orientated models such as regression and time-series analyses.     

Susceptible-infected-recovered epidemics in dynamic contact networks

Contact patterns in populations fundamentally influence the spread of infectious diseases. Current mathematical methods for epidemiological forecasting on networks largely assume that contacts between individuals are fixed, at least for the duration of an outbreak. In reality, contact patterns may be quite fluid, with individuals frequently making and breaking social or sexual relationships. Here, we develop a mathematical approach to predicting disease transmission on dynamic networks in which each individual has a characteristic behaviour (typical contact number), but the identities of their contacts change in time. We show that dynamic contact patterns shape epidemiological dynamics in ways that cannot be adequately captured in static network models or mass-action models. Our new model interpolates smoothly between static network models and mass-action models using a mixing parameter, thereby providing a bridge between disparate classes of epidemiological models. Using epidemiological and sexual contact data from an Atlanta high school, we demonstrate the application of this method for forecasting and controlling sexually transmitted disease outbreaks.     

Models of Emergency Departments for Reducing Patient Waiting Times

In this paper, we apply both agent-based models and queuing models to investigate patient access and patient flow through emergency departments. The objective of this work is to gain insights into the comparative contributions and limitations of these complementary techniques, in their ability to contribute empirical input into healthcare policy and practice guidelines. The models were developed independently, with a view to compare their suitability to emergency department simulation. The current models implement relatively simple general scenarios, and rely on a combination of simulated and real data to simulate patient flow in a single emergency department or in multiple interacting emergency departments. In addition, several concepts from telecommunications engineering are translated into this modeling context. The framework of multiple-priority queue systems and the genetic programming paradigm of evolutionary machine learning are applied as a means of forecasting patient wait times and as a means of evolving healthcare policy, respectively. The models'' utility lies in their ability to provide qualitative insights into the relative sensitivities and impacts of model input parameters, to illuminate scenarios worthy of more complex investigation, and to iteratively validate the models as they continue to be refined and extended. The paper discusses future efforts to refine, extend, and validate the models with more data and real data relative to physical (spatial–topographical) and social inputs (staffing, patient care models, etc.). Real data obtained through proximity location and tracking system technologies is one example discussed.     

Modeling the adoption of innovations in the presence of geographic and media influences

While there is a large body of work examining the effects of social network structure on innovation adoption, models to date have lacked considerations of real geography or mass media. In this article, we show these features are crucial to making more accurate predictions of a social contagion and technology adoption at a city-to-city scale. Using data from the adoption of the popular micro-blogging platform, Twitter, we present a model of adoption on a network that places friendships in real geographic space and exposes individuals to mass media influence. We show that homophily both among individuals with similar propensities to adopt a technology and geographic location is critical to reproducing features of real spatiotemporal adoption. Furthermore, we estimate that mass media was responsible for increasing Twitter's user base two to four fold. To reflect this strength, we extend traditional contagion models to include an endogenous mass media agent that responds to those adopting an innovation as well as influencing agents to adopt themselves.     

The promise of machine learning in predicting treatment outcomes in psychiatry

For many years, psychiatrists have tried to understand factors involved in response to medications or psychotherapies, in order to personalize their treatment choices. There is now a broad and growing interest in the idea that we can develop models to personalize treatment decisions using new statistical approaches from the field of machine learning and applying them to larger volumes of data. In this pursuit, there has been a paradigm shift away from experimental studies to confirm or refute specific hypotheses towards a focus on the overall explanatory power of a predictive model when tested on new, unseen datasets. In this paper, we review key studies using machine learning to predict treatment outcomes in psychiatry, ranging from medications and psychotherapies to digital interventions and neurobiological treatments. Next, we focus on some new sources of data that are being used for the development of predictive models based on machine learning, such as electronic health records, smartphone and social media data, and on the potential utility of data from genetics, electrophysiology, neuroimaging and cognitive testing. Finally, we discuss how far the field has come towards implementing prediction tools in real‐world clinical practice. Relatively few retrospective studies to‐date include appropriate external validation procedures, and there are even fewer prospective studies testing the clinical feasibility and effectiveness of predictive models. Applications of machine learning in psychiatry face some of the same ethical challenges posed by these techniques in other areas of medicine or computer science, which we discuss here. In short, machine learning is a nascent but important approach to improve the effectiveness of mental health care, and several prospective clinical studies suggest that it may be working already.     

Addressing delayed case reporting in infectious disease forecast modeling

Infectious disease forecasting is of great interest to the public health community and policymakers, since forecasts can provide insight into disease dynamics in the near future and inform interventions. Due to delays in case reporting, however, forecasting models may often underestimate the current and future disease burden.In this paper, we propose a general framework for addressing reporting delay in disease forecasting efforts with the goal of improving forecasts. We propose strategies for leveraging either historical data on case reporting or external internet-based data to estimate the amount of reporting error. We then describe several approaches for adapting general forecasting pipelines to account for under- or over-reporting of cases. We apply these methods to address reporting delay in data on dengue fever cases in Puerto Rico from 1990 to 2009 and to reports of influenza-like illness (ILI) in the United States between 2010 and 2019. Through a simulation study, we compare method performance and evaluate robustness to assumption violations. Our results show that forecasting accuracy and prediction coverage almost always increase when correction methods are implemented to address reporting delay. Some of these methods required knowledge about the reporting error or high quality external data, which may not always be available. Provided alternatives include excluding recently-reported data and performing sensitivity analysis. This work provides intuition and guidance for handling delay in disease case reporting and may serve as a useful resource to inform practical infectious disease forecasting efforts.     

Quantification of Circadian Rhythms in Single Cells

Bioluminescence techniques allow accurate monitoring of the circadian clock in single cells. We have analyzed bioluminescence data of Per gene expression in mouse SCN neurons and fibroblasts. From these data, we extracted parameters such as damping rate and noise intensity using two simple mathematical models, one describing a damped oscillator driven by noise, and one describing a self-sustained noisy oscillator. Both models describe the data well and enabled us to quantitatively characterize both wild-type cells and several mutants. It has been suggested that the circadian clock is self-sustained at the single cell level, but we conclude that present data are not sufficient to determine whether the circadian clock of single SCN neurons and fibroblasts is a damped or a self-sustained oscillator. We show how to settle this question, however, by testing the models'' predictions of different phases and amplitudes in response to a periodic entrainment signal (zeitgeber).     

Six recommendations for improving monitoring of diseases shared with wildlife: examples regarding mycobacterial infections in Spain

Monitoring is needed to identify changes in disease occurrence and to measure the impact of intervention. Using mycobacterial diseases as an example, we discuss herein the pros and cons of the current Spanish Wildlife Disease Surveillance Scheme providing suggestions for monitoring relevant diseases shared with wildlife in other regions facing similar challenges. Six points should be considered. This includes: (1) making sure the disease is properly monitored in the relevant domestic animals or even in humans; (2) also making sure that background information on wildlife population ecology is available to maximize the benefits of the monitoring effort; (3) selecting the appropriate wildlife hosts for monitoring, while being flexible enough to incorporate new ones if research suggests their participation; (4) selecting the appropriate methods for diagnosis and for time and space trend analysis; (5) deciding which parameters to target for monitoring; and finally (6) establishing a reasonable sampling effort and a suitable sampling stratification to ensure detecting changes over time and changes in response to management actions. Wildlife disease monitoring produces knowledge that benefits at least three different agencies, namely, animal health, public health and conservation, and these should combine efforts and resources. Setting up stable, comprehensive and accurate schemes at different spatial scales should become a priority. Resources are always a limiting factor, but experience shows that combined, cross-collaborative efforts allow establishing acceptable schemes with a low enough cost to be sustainable over time. These six steps for monitoring relevant shared diseases can be adapted to many other geographical settings and different disease situations.     

Data-driven habitat analysis of the Ponto-Caspian amphipod Dikerogammarus villosus in two invaded regions in Europe

When forecasting invasions, models built on a dataset from a certain region often have to be used for simulations in another geographic region. Results on the reliability and usefulness of such models are missing in literature. The present study compares habitat suitability models for the invasive amphipod species Dikerogammarus villosus developed based on data gathered in recently invaded rivers and channels in Flanders (Belgium), with similar models developed on the basis of long-term colonised systems in Croatia. The models were tested on their reliability in both regions. Two techniques, logistic regressions (LR) and classification trees (CT) were used to analyse the habitat preference of this species based on physical–chemical and morphological habitat characteristics. It was found that in Flanders, D. villosus prefers rivers with a non-natural bank structure, high oxygen saturation, low conductivity and good chemical water quality, which could be related to its distribution in large rivers and canals. In Croatian rivers, high oxygen saturation was the most important prerequisite for the species to be present. Despite the longer history of invasion in Croatia, the species seemed to have similar habitat preferences in both invaded regions. Both data-driven approaches yielded similar results, but CT performed somewhat better based on the used performance criteria (% Correctly Classified Instances, Kappa and Area Under Curve) and were easier to interpret compared to the LR. The CT models developed based on the data of Flanders performed moderately when applying on the data of Croatia, but had a lower performance when applied vice versa. The LR models did not perform well when applying on a dataset of another geographic area. Extrapolation of the logistic regression model seemed to be more difficult compared to classification tree models. Our results indicate that it is possible to determine the habitat preference of an invasive species and that these models could be applied to other regions in Europe in order to take preventive measures to control the further spread of invasive species. However, a major concern is that the models are developed based on a representative range of all relevant variables reflecting the stream conditions and that accurate data are important.     

Optimising long‐term monitoring projects for species distribution modelling: how atlas data may help

Long‐term biodiversity monitoring data are mainly used to estimate changes in species occupancy or abundance over time, but they may also be incorporated into predictive models to document species distributions in space. Although changes in occupancy or abundance may be estimated from a relatively limited number of sampling units, small sample size may lead to inaccurate spatial models and maps of predicted species distributions. We provide a methodological approach to estimate the minimum sample size needed in monitoring projects to produce accurate species distribution models and maps. The method assumes that monitoring data are not yet available when sampling strategies are to be designed and is based on external distribution data from atlas projects. Atlas data are typically collected in a large number of sampling units during a restricted timeframe and are often similar in nature to the information gathered from long‐term monitoring projects. The large number of sampling units in atlas projects makes it possible to simulate a broad gradient of sample sizes in monitoring data and to examine how the number of sampling units influences the accuracy of the models. We apply the method to several bird species using data from a regional breeding bird atlas. We explore the effect of prevalence, range size and habitat specialization of the species on the sample size needed to generate accurate models. Model accuracy is sensitive to particularly small sample sizes and levels off beyond a sufficiently large number of sampling units that varies among species depending mainly on their prevalence. The integration of spatial modelling techniques into monitoring projects is a cost‐effective approach as it offers the possibility to estimate the dynamics of species distributions in space and over time. We believe our innovative method will help in the sampling design of future monitoring projects aiming to achieve such integration.     

A scalable deep learning system for monitoring and forecasting pollutant concentration levels on UK highways

The construction of intercity highways by the government has resulted in a progressive increase in vehicle emissions and pollution from noise, dust, and vibrations despite its recognition of the air pollution menace. Efforts that have targeted roadside pollution still do not accurately monitor deadly pollutants such as nitrogen oxides and particulate matter. Reports on regional highways across the country are based on a limited number of fixed monitoring stations that are sometimes located far from the highway. These periodic and coarse-grained measurements cause inefficient highway air quality reporting, leading to inaccurate air quality forecasts. This paper, therefore, proposes and validates a scalable deep learning framework for efficiently capturing fine-grained highway data and forecasting future concentration levels. Highways in four different UK regions - Newport, Lewisham, Southwark, and Chepstow were used as case studies to develop a REVIS system and validate the proposed framework. REVIS examined the framework's ability to capture granular pollution data, scale up its storage facility to rapid data growth and translate high-level user queries to structured query language (SQL) required for exploratory data analysis. Finally, the framework's suitability for predictive analytics was tested using fastai's library for tabular data, and automated hyperparameter tuning was implemented using bayesian optimisation. The results of our experiments demonstrate the suitability of the proposed framework in building end-to-end systems for extensive monitoring and forecasting of pollutant concentration levels on highways. The study serves as a background for future related research looking to improve the overall performance of roadside and highway air quality forecasting models.     

Efficient MILP formulations for the optimal synthesis of chromatographic protein purification processes

The use of recombinant proteins has increased greatly in recent years, as well as the techniques used for their purification. The selection of an efficient process to purify proteins is a major bottleneck found when trying to scale up results obtained in the laboratory to a large-scale industrial process. One of the main challenges in the synthesis of downstream purification stages in biotechnological processes is the appropriate selection and sequencing of chromatographic steps. The objective of this work is to develop mixed integer linear programming models for the synthesis of protein purification processes. Models for each chromatographic technique rely on physicochemical data of a protein mixture, which contains the desired product and provide information on its potential purification. Formulations that are based on convex hull representations are proposed to calculate the minimum number of steps from a set of chromatographic techniques that must achieve a specified purity level and alternatively to maximize purity for a given number of steps. The proposed models are tested in several examples with experimental data and present time reductions of up to three orders of magnitude when compared to big-M formulations.