Prediction of Microcystis Occurrences and Analysis Using Machine Learning in High-Dimension, Low-Sample-Size and Imbalanced Water Quality Data

Harmful Algae, Год журнала: 2022, Номер 117, С. 102273 - 102273

Опубликована: Июнь 25, 2022

Язык: Английский

---

Forecasting seed production in perennial plants: identifying challenges and charting a path forward

New Phytologist, Год журнала: 2023, Номер 239(2), С. 466 - 476

Опубликована: Май 18, 2023

Summary Interannual variability of seed production, known as masting, has far‐reaching ecological impacts including effects on forest regeneration and the population dynamics consumers. Because relative timing management conservation efforts in ecosystems dominated by masting species often determines their success, there is a need to study mechanisms develop forecasting tools for production. Here, we aim establish production new branch discipline. We evaluate predictive capabilities three models – foreMast, Δ T , sequential model designed predict trees using pan‐European dataset Fagus sylvatica The are moderately successful recreating dynamics. availability high‐quality data prior improved model's power, suggesting that effective monitoring methods crucial creating tools. In terms extreme events, better at predicting crop failures than bumper crops, likely because factors preventing understood processes leading large reproductive events. summarize current challenges provide roadmap help advance discipline encourage further development mast forecasting.

Язык: Английский

---

Forecasting the abundance of disease vectors with deep learning

Ecological Informatics, Год журнала: 2023, Номер 78, С. 102272 - 102272

Опубликована: Авг. 20, 2023

Arboviral diseases such as dengue, Zika, chikungunya or yellow fever are a worldwide concern. The abundance of vector species plays key role in the emergence outbreaks these diseases, so forecasting numbers is fundamental preventive risk assessment. Here we describe and demonstrate novel approach that uses state-of-the-art deep learning algorithms to forecast disease abundances. Unlike classical statistical machine methods, models use time series data directly predictors identify features most relevant from predictive perspective. We for first application this predict short-term temporal trends number Aedes aegypti mosquito eggs across Madeira Island period 2013 2019. Specifically, apply whether, following week, Ae. will remain unchanged, whether it increase decrease, considering different percentages change. obtained high performance all years considered (mean AUC = 0.92 ± 0.05 SD). Our performed better than methods. also found preceding highly informative predictor future trends. Linking our transmission importation contribute operational, early warning systems arboviral risk.

Язык: Английский

---

Increase in MJO predictability under global warming

Nature Climate Change, Год журнала: 2023, Номер 14(1), С. 68 - 74

Опубликована: Дек. 20, 2023

Язык: Английский

---

Early detection of sea lice epidemic transitions and changes in long-term abundance levels in salmon farming areas

Aquaculture, Год журнала: 2025, Номер unknown, С. 742385 - 742385

Опубликована: Март 1, 2025

Язык: Английский

---