Dataset Information

Machine learning modeling of plant phenology based on coupling satellite and gridded meteorological dataset.

ABSTRACT: Changes in the timing of plant phenological phases are important proxies in contemporary climate research. However, most of the commonly used traditional phenological observations do not give any coherent spatial information. While consistent spatial data can be obtained from airborne sensors and preprocessed gridded meteorological data, not many studies robustly benefit from these data sources. Therefore, the main aim of this study is to create and evaluate different statistical models for reconstructing, predicting, and improving quality of phenological phases monitoring with the use of satellite and meteorological products. A quality-controlled dataset of the 13 BBCH plant phenophases in Poland was collected for the period 2007-2014. For each phenophase, statistical models were built using the most commonly applied regression-based machine learning techniques, such as multiple linear regression, lasso, principal component regression, generalized boosted models, and random forest. The quality of the models was estimated using a k-fold cross-validation. The obtained results showed varying potential for coupling meteorological derived indices with remote sensing products in terms of phenological modeling; however, application of both data sources improves models' accuracy from 0.6 to 4.6 day in terms of obtained RMSE. It is shown that a robust prediction of early phenological phases is mostly related to meteorological indices, whereas for autumn phenophases, there is a stronger information signal provided by satellite-derived vegetation metrics. Choosing a specific set of predictors and applying a robust preprocessing procedures is more important for final results than the selection of a particular statistical model. The average RMSE for the best models of all phenophases is 6.3, while the individual RMSE vary seasonally from 3.5 to 10 days. Models give reliable proxy for ground observations with RMSE below 5 days for early spring and late spring phenophases. For other phenophases, RMSE are higher and rise up to 9-10 days in the case of the earliest spring phenophases.

SUBMITTER: Czernecki B

PROVIDER: S-EPMC6028898 | biostudies-other | 2018 Jul

REPOSITORIES: biostudies-other

ACCESS DATA

Publications

Machine learning modeling of plant phenology based on coupling satellite and gridded meteorological dataset.

Czernecki Bartosz B Nowosad Jakub J Jabłońska Katarzyna K

International journal of biometeorology 20180411 7

Changes in the timing of plant phenological phases are important proxies in contemporary climate research. However, most of the commonly used traditional phenological observations do not give any coherent spatial information. While consistent spatial data can be obtained from airborne sensors and preprocessed gridded meteorological data, not many studies robustly benefit from these data sources. Therefore, the main aim of this study is to create and evaluate different statistical models for reco ...[more]

PMID: 29644431

Shared Molecules

Only show the datasets with similarity scores above: 0.5

Threshold

0.5

Similar Datasets

Project description:IntroductionHeatstroke is a serious clinical condition caused by exposure to high temperature and high humidity environment, which leads to a rapid increase of the core temperature of the body to more than 40°C, accompanied by skin burning, consciousness disorders and other organ system damage. This study aims to analyze the effect of meteorological factors on the incidence of heatstroke using machine learning, and to construct a heatstroke forecasting model to provide reference for heatstroke prevention.MethodsThe data of heatstroke incidence and meteorological factors in a city in South China from May to September 2014-2019 were analyzed in this study. The lagged effect of meteorological factors on heatstroke incidence was analyzed based on the distributed lag non-linear model, and the prediction model was constructed by using regression decision tree, random forest, gradient boosting trees, linear SVRs, LSTMs, and ARIMA algorithm.ResultsThe cumulative lagged effect found that heat index, dew-point temperature, daily maximum temperature and relative humidity had the greatest influence on heatstroke. When the heat index, dew-point temperature, and daily maximum temperature exceeded certain thresholds, the risk of heatstroke was significantly increased on the same day and within the following 5 days. The lagged effect of relative humidity on the occurrence of heatstroke was different with the change of relative humidity, and both excessively high and low environmental humidity levels exhibited a longer lagged effect on the occurrence of heatstroke. With regard to the prediction model, random forest model had the best performance of 5.28 on RMSE and dropped to 3.77 after being adjusted.DiscussionThe incidence of heatstroke in this city is significantly correlated with heat index, heatwave, dew-point temperature, air temperature and zhongfu, among which the heat index and dew-point temperature have a significant lagged effect on heatstroke incidence. Relevant departments need to closely monitor the data of the correlated factors, and adopt heat prevention measures before the temperature peaks, calling on citizens to reduce outdoor activities.

Project description:The effect of climatically-driven plant phenology on mammalian reproduction is one key to predicting species-specific demographic responses to climate change. Large ungulates face their greatest energetic demands from the later stages of pregnancy through weaning, and so in seasonal environments parturition dates should match periods of high primary productivity. Interannual variation in weather influences the quality and timing of forage availability, which can influence neonatal survival. Here, we evaluated macro-scale patterns in reproductive performance of a widely distributed ungulate (mule deer, Odocoileus hemionus) across contrasting climatological regimes using satellite-derived indices of primary productivity and plant phenology over eight degrees of latitude (890 km) in the American Southwest. The dataset comprised > 180,000 animal observations taken from 54 populations over eight years (2004-2011). Regionally, both the start and peak of growing season ("Start" and "Peak", respectively) are negatively and significantly correlated with latitude, an unusual pattern stemming from a change in the dominance of spring snowmelt in the north to the influence of the North American Monsoon in the south. Corresponding to the timing and variation in both the Start and Peak, mule deer reproduction was latest, lowest, and most variable at lower latitudes where plant phenology is timed to the onset of monsoonal moisture. Parturition dates closely tracked the growing season across space, lagging behind the Start and preceding the Peak by 27 and 23 days, respectively. Mean juvenile production increased, and variation decreased, with increasing latitude. Temporally, juvenile production was best predicted by primary productivity during summer, which encompassed late pregnancy, parturition, and early lactation. Our findings offer a parsimonious explanation of two key reproductive parameters in ungulate demography, timing of parturition and mean annual production, across latitude and changing climatological regimes. Practically, this demonstrates the potential for broad-scale modeling of couplings between climate, plant phenology, and animal populations using space-borne observations.

Project description:Background:Hospital readmission prediction in pediatric hospitals has received little attention. Studies have focused on the readmission frequency analysis stratified by disease and demographic/geographic characteristics but there are no predictive modeling approaches, which may be useful to identify preventable readmissions that constitute a major portion of the cost attributed to readmissions. Objective:To assess the all-cause readmission predictive performance achieved by machine learning techniques in the emergency department of a pediatric hospital in Santiago, Chile. Materials:An all-cause admissions dataset has been collected along six consecutive years in a pediatric hospital in Santiago, Chile. The variables collected are the same used for the determination of the child's treatment administrative cost. Methods:Retrospective predictive analysis of 30-day readmission was formulated as a binary classification problem. We report classification results achieved with various model building approaches after data curation and preprocessing for correction of class imbalance. We compute repeated cross-validation (RCV) with decreasing number of folders to assess performance and sensitivity to effect of imbalance in the test set and training set size. Results:Increase in recall due to SMOTE class imbalance correction is large and statistically significant. The Naive Bayes (NB) approach achieves the best AUC (0.65); however the shallow multilayer perceptron has the best PPV and f-score (5.6 and 10.2, resp.). The NB and support vector machines (SVM) give comparable results if we consider AUC, PPV, and f-score ranking for all RCV experiments. High recall of deep multilayer perceptron is due to high false positive ratio. There is no detectable effect of the number of folds in the RCV on the predictive performance of the algorithms. Conclusions:We recommend the use of Naive Bayes (NB) with Gaussian distribution model as the most robust modeling approach for pediatric readmission prediction, achieving the best results across all training dataset sizes. The results show that the approach could be applied to detect preventable readmissions.

Dataset Information

Machine learning modeling of plant phenology based on coupling satellite and gridded meteorological dataset.

Publications

Machine learning modeling of plant phenology based on coupling satellite and gridded meteorological dataset.

Shared Molecules

Only show the datasets with similarity scores above: 0.5

Threshold

0.5

Similar Datasets

OmicsDI is part of the ELIXIR infrastructure

Tweets