Forecasting Pollen Aerobiology with Modis EVI, Land Cover, and Phenology Using Machine Learning Tools

Huete, Alfredo; Tran, Ngoc Nguyen; Nguyen, Ha; Xie, Qiaoyun; Constance, Katelaris

doi:10.1109/igarss.2019.8898796

Cited by 6 publications

(3 citation statements)

References 7 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…To improve the capacity and accuracy of pollen forecast, satellite‐derived vegetation phenology should be incorporated to track the up‐to‐date composition and biogeographical distribution of species and their seasonal timings (Campbell et al, 2020 ; Davies et al, 2021 ). This ecological information will provide insights into patterns of pollen release and distribution and prediction of future pollen outbreaks (Huete et al, 2019 ).…”

Section: Land Surface Phenology and Human Healthmentioning

confidence: 99%

Monitoring nature's calendar from space: Emerging topics in land surface phenology and associated opportunities for science applications

Zhu

Xie

et al. 2022

Global Change Biology

Self Cite

View full text Add to dashboard Cite

Vegetation phenology has been viewed as the nature's calendar and an integrative indicator of plant-climate interactions. The correct representation of vegetation phenology is important for models to accurately simulate the exchange of carbon, water, and energy between the vegetated land surface and the atmosphere. Remote sensing has advanced the monitoring of vegetation phenology by providing spatially and temporally continuous data that together with conventional ground observations offers a unique contribution to our knowledge about the environmental impact on ecosystems as well as the ecological adaptations and feedback to global climate change. Land surface phenology (LSP) is defined as the use of satellites to monitor seasonal dynamics in vegetated land surfaces and to estimate phenological transition dates. LSP, as an interdisciplinary subject among remote sensing, ecology, and biometeorology, has undergone rapid development over the past few decades. Recent advances in sensor technologies, as well as data fusion techniques, have enabled novel phenology retrieval algorithms that refine phenology details at even higher spatiotemporal resolutions, providing new insights into ecosystem dynamics. As such, here we summarize the recent advances in LSP and the associated opportunities for science applications. We focus on the remaining challenges, promising techniques, and emerging topics that together we believe will truly form the very frontier of the global LSP research field.

show abstract

Section: Land Surface Phenology and Human Healthmentioning

confidence: 99%

Monitoring nature's calendar from space: Emerging topics in land surface phenology and associated opportunities for science applications

Zhu

Xie

et al. 2022

Global Change Biology

Self Cite

View full text Add to dashboard Cite

show abstract

“…It is therefore challenging to extrapolate locally-trained pollen models to locations without prior in-situ data collection. Integration of land surface phenology as predictors has been suggested to improve data-driven models (Huete et al, 2019;F. Lo et al, 2021) .…”

Section: Introductionmentioning

confidence: 99%

“…Interannual variations in the flowering time of multiple plant functional types have been explained by remotely sensed green-up time (Delbart et al, 2015) . Moving beyond correlation, data-driven predictive pollen models have also benefited from incorporating MODIS Enhanced Vegetation Index (EVI) as a predictor (Huete et al, 2019;F. A.…”

Section: Introductionmentioning

confidence: 99%

Predicting reproductive phenology of wind-pollinated trees via PlanetScope time series

Song,

Katz,

Zhu

et al. 2024

Preprint

View full text Add to dashboard Cite

Airborne pollen triggers allergic reactions which result in public health consequences. A better understanding of flowering and pollen phenology could improve airborne pollen predictions and reduce pollen exposure. Data on the timing of flowering and pollen release are needed to improve models of airborne pollen concentrations, but existingin-situdata collection efforts are expensive and spatially sparse. Satellite-based estimates of plant phenology could potentially enable large-scale data collection, but it is difficult to detect the reproductive phenology of wind-pollinated flowers from space. Here, we infer the reproductive phenology of wind-pollinated plants usingPlanetScopetime series with a spatial resolution of 3 m and a daily revisit cycle, complemented byin-situflower and pollen observations, leveraging the correlation between vegetative and reproductive phenology. On the individual tree level, we extracted PlanetScope-derived green-up time and validated its correlation to flowering time using flower observations in a national-scale observatory network. Scaling up to the city level, we developed a novel approach to characterize pollen phenology from PlanetScope-derived vegetative phenology, by optimizing two tuning parameters: the threshold of green-up or green-down and the time lag between green-up/down and flowering. We applied this method to seven cities in the US and seven key wind-pollinated tree genera, calibrated by measurements of airborne pollen concentrations. Our method characterized pollen phenology accurately, not only in-sample (Spearman correlation: 0.751, nRMSE: 13.5%) but also out-of-sample (Spearman correlation: 0.691, nRMSE: 14.5%). Using the calibrated model, we further mapped the pollen phenology landscape within cities, showing intra-urban heterogeneity. Using high spatiotemporal resolution remote sensing, our novel approach enables us to infer the flowering and pollen phenology of wind-pollinated plant taxa on a large scale and a fine resolution, including areas with limited priorin-situflower and pollen observations. The use of PlanetScope time series therefore holds promise for developing process-based pollen models and targeted public health strategies to mitigate the impact of allergenic pollen exposure.

show abstract

Machine learning in landscape ecological analysis: a review of recent approaches

et al. 2021

View full text Add to dashboard Cite

Forecasting Pollen Aerobiology with Modis EVI, Land Cover, and Phenology Using Machine Learning Tools

Cited by 6 publications

References 7 publications

Monitoring nature's calendar from space: Emerging topics in land surface phenology and associated opportunities for science applications

Monitoring nature's calendar from space: Emerging topics in land surface phenology and associated opportunities for science applications

Predicting reproductive phenology of wind-pollinated trees via PlanetScope time series

Machine learning in landscape ecological analysis: a review of recent approaches

Contact Info

Product

Resources

About