Applying Deep Neural Networks and Ensemble Machine Learning Methods to Forecast Airborne Ambrosia Pollen

Forecasting daily total pollen concentrations on a global scale

BACKGROUND

There is evidence that global anthropogenic climate change may be impacting floral phenology and the temporal and spatial characteristics of aero-allergenic pollen. Given the extent of current and future climate uncertainty, there is a need to strengthen predictive pollen forecasts.

METHODS

The study aims to use CatBoost (CB) and deep learning (DL) models for predicting the daily total pollen concentration up to 14 days in advance for 23 cities, covering all five continents. The model includes the projected environmental parameters, recent concentrations (1, 2 and 4 weeks), and the past environmental explanatory variables, and their future values.

RESULTS

The best pollen forecasts include Mexico City (R2(DL_7) ≈ .7), and Santiago (R2(DL_7) ≈ .8) for the 7th forecast day, respectively; while the weakest pollen forecasts are made for Brisbane (R2(DL_7) ≈ .4) and Seoul (R2(DL_7) ≈ .1) for the 7th forecast day. The global order of the five most important environmental variables in determining the daily total pollen concentrations is, in decreasing order: the past daily total pollen concentration, future 2 m temperature, past 2 m temperature, past soil temperature in 28-100 cm depth, and past soil temperature in 0-7 cm depth. City-related clusters of the most similar distribution of feature importance values of the environmental variables only slightly change on consecutive forecast days for Caxias do Sul, Cape Town, Brisbane, and Mexico City, while they often change for Sydney, Santiago, and Busan.

CONCLUSIONS

This new knowledge of the ecological relationships of the most remarkable variables importance for pollen forecast models according to clusters, cities and forecast days is important for developing and improving the accuracy of airborne pollen forecasts.

A deep learning LSTM-based approach for forecasting annual pollen curves: Olea and Urticaceae pollen types as a case study

Airborne pollen can trigger allergic rhinitis and other respiratory diseases in the synthesised population, which makes it one of the most relevant biological contaminants. Therefore, implementing accurate forecast systems is a priority for public health. The current forecast models are generally useful, but they falter when long time series of data are managed. The emergence of new computational techniques such as the LSTM algorithms could constitute a significant improvement for the pollen risk assessment. In this study, several LSTM variants were applied to forecast monthly pollen integrals in Málaga (southern Spain) using meteorological variables as predictors. Olea and Urticaceae pollen types were modelled as proxies of different annual pollen curves, using data from the period 1992-2022. The aims of this study were to determine the LSTM variants with the highest accuracy when forecasting monthly pollen integrals as well as to compare their performance with the traditional pollen forecast methods. The results showed that the CNN-LSTM were the most accurate when forecasting the monthly pollen integrals for both pollen types. Moreover, the traditional forecast methods were outperformed by all the LSTM variants. These findings highlight the importance of implementing LSTM models in pollen forecasting for public health and research applications.

A temporally and spatially explicit, data-driven estimation of airborne ragweed pollen concentrations across Europe

Ongoing and future climate change driven expansion of aeroallergen-producing plant species comprise a major human health problem across Europe and elsewhere. There is an urgent need to produce accurate, temporally dynamic maps at the continental level, especially in the context of climate uncertainty. This study aimed to restore missing daily ragweed pollen data sets for Europe, to produce phenological maps of ragweed pollen, resulting in the most complete and detailed high-resolution ragweed pollen concentration maps to date. To achieve this, we have developed two statistical procedures, a Gaussian method (GM) and deep learning (DL) for restoring missing daily ragweed pollen data sets, based on the plant's reproductive and growth (phenological, pollen production and frost-related) characteristics. DL model performances were consistently better for estimating seasonal pollen integrals than those of the GM approach. These are the first published modelled maps using altitude correction and flowering phenology to recover missing pollen information. We created a web page (http://euragweedpollen.gmf.u-szeged.hu/), including daily ragweed pollen concentration data sets of the stations examined and their restored daily data, allowing one to upload newly measured or recovered daily data. Generation of these maps provides a means to track pollen impacts in the context of climatic shifts, identify geographical regions with high pollen exposure, determine areas of future vulnerability, apply spatially-explicit mitigation measures and prioritize management interventions.

EAACI guidelines on environmental science in allergic diseases and asthma - Leveraging artificial intelligence and machine learning to develop a causality model in exposomics

Allergic diseases and asthma are intrinsically linked to the environment we live in and to patterns of exposure. The integrated approach to understanding the effects of exposures on the immune system includes the ongoing collection of large-scale and complex data. This requires sophisticated methods to take full advantage of what this data can offer. Here we discuss the progress and further promise of applying artificial intelligence and machine-learning approaches to help unlock the power of complex environmental data sets toward providing causality models of exposure and intervention. We discuss a range of relevant machine-learning paradigms and models including the way such models are trained and validated together with examples of machine learning applied to allergic disease in the context of specific environmental exposures as well as attempts to tie these environmental data streams to the full representative exposome. We also discuss the promise of artificial intelligence in personalized medicine and the methodological approaches to healthcare with the final AI to improve public health.

High Spatial-Temporal PM2.5 Modeling Utilizing Next Generation Weather Radar (NEXRAD) as a Supplementary Weather Source

PM2.5, a type of fine particulate with a diameter equal to or less than 2.5 micrometers, has been identified as a major source of air pollution, and is associated with many health issues. Research on utilizing various data sources, such as remote sensing and in situ sensors, for PM2.5 concentrations modeling remains a hot topic. In this study, the Next Generation Weather Radar (NEXRAD) is used as a supplementary weather data source, along with European Centre for Medium-Range Weather Forecasts (ECMWF), solar angles, and Geostationary Operational Environmental Satellite (GOES16) Aerosol Optical Depth (AOD) to model high spatial-temporal PM2.5 concentrations. PM2.5 concentrations as well as in situ weather condition variables are collected from the 31 sensors that are deployed in the Dallas Metropolitan area. Four machine learning models with different predictor variables are developed based on an ensemble approach. Since in situ weather observations are not widely available, ECMWF is used as an alternative data source for weather conditions in studies. Hence, the four established models are compared in three groups. Both models in this first group use weather variables collected from deployed sensors, but one uses NEXRAD and the other does not. In the second group, the two models use weather variables retrieved from ECMWF, one using NEXRAD and one without. In the third group, one model uses weather variables from ECMWF, and the other uses in situ weather variables, both without NEXRAD. The first two environmental groups investigate how NEXRAD can enhance model performances with weather variables collected from in situ observations and ECMWF, respectively. The third group explores how effective using ECMWF as an alternative source of weather conditions. Based on the results, the incorporation of NEXRAD achieves an R2 score of 0.86 and 0.83 for groups 1 and 2, respectively, for an improvement of 2.8% and 9.6% over those models without NEXRAD. For group three, the use of ECMWF as an alternative source of in situ weather observations results in a 0.13 R2 drop. For PM2.5 estimation, weather variables including precipitation, temperature, pressure, and surface pressure from ECMWF and deployed sensors, as well as NEXRAD velocity, are shown to be significant factors.

Pollen forecasting and its relevance in pollen allergen avoidance

Pollinosis and allergic asthma are respiratory diseases of global relevance, heavily affecting the quality of life of allergic subjects. Since there is not a decisive cure yet, pollen allergic subjects need to avoid exposure to high pollen allergens concentrations. For this purpose, pollen forecasting is an essential tool that needs to be reliable and easily accessible. While forecasting methods are rapidly evolving towards more complex statistical and physical models, the use of simple and traditional methods is still preferred in routine predictions. In this review, we summarise and explain the main parameters considered when forecasting pollen, and classify the different forecasting methods in two groups: observation-based and process-based. Finally, we compare these approaches based on their usefulness to allergic patients, and discuss possible future developments of the field.

Autonomous Learning of New Environments with a Robotic Team Employing Hyper-Spectral Remote Sensing, Comprehensive In-Situ Sensing and Machine Learning

This paper describes and demonstrates an autonomous robotic team that can rapidly learn the characteristics of environments that it has never seen before. The flexible paradigm is easily scalable to multi-robot, multi-sensor autonomous teams, and it is relevant to satellite calibration/validation and the creation of new remote sensing data products. A case study is described for the rapid characterisation of the aquatic environment, over a period of just a few minutes we acquired thousands of training data points. This training data allowed for our machine learning algorithms to rapidly learn by example and provide wide area maps of the composition of the environment. Along side these larger autonomous robots two smaller robots that can be deployed by a single individual were also deployed (a walking robot and a robotic hover-board), observing significant small scale spatial variability.

Precision Medicine, AI, and the Future of Personalized Health Care

The convergence of artificial intelligence (AI) and precision medicine promises to revolutionize health care. Precision medicine methods identify phenotypes of patients with less‐common responses to treatment or unique healthcare needs. AI leverages sophisticated computation and inference to generate insights, enables the system to reason and learn, and empowers clinician decision making through augmented intelligence. Recent literature suggests that translational research exploring this convergence will help solve the most difficult challenges facing precision medicine, especially those in which nongenomic and genomic determinants, combined with information from patient symptoms, clinical history, and lifestyles, will facilitate personalized diagnosis and prognostication.

Deep Learning to Unveil Correlations between Urban Landscape and Population Health

The global healthcare landscape is continuously changing throughout the world as technology advances, leading to a gradual change in lifestyle. Several diseases such as asthma and cardiovascular conditions are becoming more diffuse, due to a rise in pollution exposure and a more sedentary lifestyle. Healthcare providers deal with increasing new challenges, and thanks to fast-developing big data technologies, they can be faced with systems that provide direct support to citizens. In this context, within the EU-funded Participatory Urban Living for Sustainable Environments (PULSE) project, we are implementing a data analytic platform designed to provide public health decision makers with advanced approaches, to jointly analyze maps and geospatial information with healthcare and air pollution data. In this paper we describe a component of such platforms, which couples deep learning analysis of urban geospatial images with healthcare indexes collected by the 500 Cities project. By applying a pre-learned deep Neural Network architecture, satellite images of New York City are analyzed and latent feature variables are extracted. These features are used to derive clusters, which are correlated with healthcare indicators by means of a multivariate classification model. Thanks to this pipeline, it is possible to show that, in New York City, health care indexes are significantly correlated to the urban landscape. This pipeline can serve as a basis to ease urban planning, since the same interventions can be organized on similar areas, even if geographically distant.

Using Machine Learning for the Calibration of Airborne Particulate Sensors

Airborne particulates are of particular significance for their human health impacts and their roles in both atmospheric radiative transfer and atmospheric chemistry. Observations of airborne particulates are typically made by environmental agencies using rather expensive instruments. Due to the expense of the instruments usually used by environment agencies, the number of sensors that can be deployed is limited. In this study we show that machine learning can be used to effectively calibrate lower cost optical particle counters. For this calibration it is critical that measurements of the atmospheric pressure, humidity, and temperature are also made.

Geographical Imputation of Missing Poaceae Pollen Data via Convolutional Neural Networks

Airborne pollen monitoring datasets sometimes exhibit gaps, even very long, either because of maintenance or because of a lack of expert personnel. Despite the numerous imputation techniques available, not all of them effectively include the spatial relations of the data since the assumption of missing-at-random is made. However, there are several techniques in geostatistics that overcome this limitation such as the inverse distance weighting and Gaussian processes or kriging. In this paper, a new method is proposed that utilizes convolutional neural networks. This method not only shows a competitive advantage in terms of accuracy when compared to the aforementioned techniques by improving the error by 5% on average, but also reduces execution training times by 90% when compared to a Gaussian process. To show the advantages of the proposal, 10%, 20%, and 30% of the data points are removed in the time series of a Poaceae pollen observation station in the region of Madrid, and the airborne concentrations from the remaining available stations in the network are used to impute the data removed. Even though the improvements in terms of accuracy are not significantly large, even if consistent, the gain in computational time and the flexibility of the proposed convolutional neural network allow field experts to adapt and extend the solution, for instance including meteorological variables, with the potential decrease of the errors reported in this paper.