Dataset Information

Automated data-intensive forecasting of plant phenology throughout the United States.

ABSTRACT: Phenology, the timing of cyclical and seasonal natural phenomena such as flowering and leaf out, is an integral part of ecological systems with impacts on human activities like environmental management, tourism, and agriculture. As a result, there are numerous potential applications for actionable predictions of when phenological events will occur. However, despite the availability of phenological data with large spatial, temporal, and taxonomic extents, and numerous phenology models, there have been no automated species-level forecasts of plant phenology. This is due in part to the challenges of building a system that integrates large volumes of climate observations and forecasts, uses that data to fit models and make predictions for large numbers of species, and consistently disseminates the results of these forecasts in interpretable ways. Here, we describe a new near-term phenology-forecasting system that makes predictions for the timing of budburst, flowers, ripe fruit, and fall colors for 78 species across the United States up to 6 months in advance and is updated every four days. We use the lessons learned in developing this system to provide guidance developing large-scale near-term ecological forecast systems more generally, to help advance the use of automated forecasting in ecology.

SUBMITTER: Taylor SD

PROVIDER: S-EPMC9285964 | biostudies-literature | 2020 Jan

REPOSITORIES: biostudies-literature

ACCESS DATA

Publications

Automated data-intensive forecasting of plant phenology throughout the United States.

Taylor Shawn D SD White Ethan P EP

Ecological applications : a publication of the Ecological Society of America 20191125 1

Phenology, the timing of cyclical and seasonal natural phenomena such as flowering and leaf out, is an integral part of ecological systems with impacts on human activities like environmental management, tourism, and agriculture. As a result, there are numerous potential applications for actionable predictions of when phenological events will occur. However, despite the availability of phenological data with large spatial, temporal, and taxonomic extents, and numerous phenology models, there have ...[more]

PMID: 31630468

Similar Datasets

Project description:Climate change has been shown to advance spring phenology, increase the number of insect generations per year (multivoltinism) and increase pathogen infection levels. However, we lack insights into the effects of plant spring phenology and the biotic environment on the preference and performance of multivoltine herbivores and whether such effects extend into the later part of the growing season. To this aim, we used a multifactorial growth chamber experiment to examine the influence of spring phenology on plant pathogen infection, and how the independent and interactive effects of spring phenology and plant pathogen infection affect the preference and performance of multigenerational attackers (the leaf miner Tischeria ekebladella and the aphid Tuberculatus annulatus) on the pedunculate oak in the early, mid and late parts of the plant growing season. Pathogen infection was highest on late phenology plants, irrespective of whether inoculations were conducted in the early, mid or late season. The leaf miner consistently preferred to oviposit on middle and late phenology plants, as well as healthy plants, during all parts of the growing season, whereas we detected an interactive effect between spring phenology and pathogen infection on the performance of the leaf miner. Aphids preferred healthy, late phenology plants during the early season, healthy plants during the mid season, and middle phenology plants during the late season, whereas aphid performance was consistently higher on healthy plants during all parts of the growing season. Our findings highlight that the impact of spring phenology on pathogen infection and the preference and performance of insect herbivores is not restricted to the early season, but that its imprint is still present - and sometimes equally strong - during the peak and end of the growing season. Plant pathogens generally negatively affected herbivore preference and performance, and modulated the effects of spring phenology. We conclude that spring phenology and pathogen infection are two important factors shaping the preference and performance of multigenerational plant attackers, which is particularly relevant given the current advance in spring phenology, pathogen outbreaks and increase in voltinism with climate change.

Project description:The promise of machine learning successfully exploiting digital phenotyping data to forecast mental states in psychiatric populations could greatly improve clinical practice. Previous research focused on binary classification and continuous regression, disregarding the often ordinal nature of prediction targets derived from clinical rating scales. In addition, mental health ratings typically show important class imbalance or skewness that need to be accounted for when evaluating predictive performance. Besides it remains unclear which machine learning algorithm is best suited for forecast tasks, the eXtreme Gradient Boosting (XGBoost) and long short-term memory (LSTM) algorithms being 2 popular choices in digital phenotyping studies. The CrossCheck dataset includes 6,364 mental state surveys using 4-point ordinal rating scales and 23,551 days of smartphone sensor data contributed by patients with schizophrenia. We trained 120 machine learning models to forecast 10 mental states (e.g., Calm, Depressed, Seeing things) from passive sensor data on 2 predictive tasks (ordinal regression, binary classification) with 2 learning algorithms (XGBoost, LSTM) over 3 forecast horizons (same day, next day, next week). A majority of ordinal regression and binary classification models performed significantly above baseline, with macro-averaged mean absolute error values between 1.19 and 0.77, and balanced accuracy between 58% and 73%, which corresponds to similar levels of performance when these metrics are scaled. Results also showed that metrics that do not account for imbalance (mean absolute error, accuracy) systematically overestimated performance, XGBoost models performed on par with or better than LSTM models, and a significant yet very small decrease in performance was observed as the forecast horizon expanded. In conclusion, when using performance metrics that properly account for class imbalance, ordinal forecast models demonstrated comparable performance to the prevalent binary classification approach without losing valuable clinical information from self-reports, thus providing richer and easier to interpret predictions.

Dataset Information

Automated data-intensive forecasting of plant phenology throughout the United States.

Publications

Automated data-intensive forecasting of plant phenology throughout the United States.

Similar Datasets

OmicsDI is part of the ELIXIR infrastructure

Tweets