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

Similar Datasets

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.

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.

Similar Datasets

OmicsDI is part of the ELIXIR infrastructure

Tweets