scholarly journals Spatio-Temporal Prediction of the Epidemic Spread of Dangerous Pathogens Using Machine Learning Methods

2020 ◽  
Vol 9 (1) ◽  
pp. 44 ◽  
Author(s):  
Wolfgang B. Hamer ◽  
Tim Birr ◽  
Joseph-Alexander Verreet ◽  
Rainer Duttmann ◽  
Holger Klink
Keyword(s):  
Machine Learning ◽  
Powdery Mildew ◽  
Regional Scale ◽  
R Package ◽  
Good Time ◽  
Climate Information ◽  
Learning Methods ◽  
Temporal Prediction ◽  
Machine Learning Methods ◽  
Weather And Climate

Real-time identification of the occurrence of dangerous pathogens is of crucial importance for the rapid execution of countermeasures. For this purpose, spatial and temporal predictions of the spread of such pathogens are indispensable. The R package papros developed by the authors offers an environment in which both spatial and temporal predictions can be made, based on local data using various deterministic, geostatistical regionalisation, and machine learning methods. The approach is presented using the example of a crops infection by fungal pathogens, which can substantially reduce the yield if not treated in good time. The situation is made more difficult by the fact that it is particularly difficult to predict the behaviour of wind-dispersed pathogens, such as powdery mildew (Blumeria graminis f. sp. tritici). To forecast pathogen development and spatial dispersal, a modelling process scheme was developed using the aforementioned R package, which combines regionalisation and machine learning techniques. It enables the prediction of the probability of yield- relevant infestation events for an entire federal state in northern Germany at a daily time scale. To run the models, weather and climate information are required, as is knowledge of the pathogen biology. Once fitted to the pathogen, only weather and climate information are necessary to predict such events, with an overall accuracy of 68% in the case of powdery mildew at a regional scale. Thereby, 91% of the observed powdery mildew events are predicted.

scholarly journals Evaluating Different Machine Learning Methods for Upscaling Evapotranspiration from Flux Towers to the Regional Scale

2018 ◽  
Vol 123 (16) ◽  
pp. 8674-8690 ◽  
Author(s):  
Tongren Xu ◽  
Zhixia Guo ◽  
Shaomin Liu ◽  
Xinlei He ◽  
Yangfanyu Meng ◽  
...  
Keyword(s):  
Machine Learning ◽  
Regional Scale ◽  
Learning Methods ◽  
Machine Learning Methods

scholarly journals learnMET: an R package to apply machine learning methods for genomic prediction using multi-environment trial data

2021 ◽  
Author(s):  
Cathy C. Westhues ◽  
Henner Simianer ◽  
Timothy M. Beissinger
Keyword(s):  
Machine Learning ◽  
Genomic Prediction ◽  
Prediction Models ◽  
R Package ◽  
Fixed Number ◽  
Environmental Data ◽  
Weather Data ◽  
Learning Methods ◽  
Machine Learning Methods ◽  
Daily Weather Data

We introduce the R-package learnMET, developed as a flexible framework to enable a collection of analyses on multi-environment trial (MET) breeding data with machine learning-based models. learnMET allows the combination of genomic information with environmental data such as climate and/or soil characteristics. Notably, the package offers the possibility of incorporating weather data from field weather stations, or can retrieve global meteorological datasets from a NASA database. Daily weather data can be aggregated in daily windows based on naive (for instance, daily windows with a fixed number of days) or phenological approaches. Different machine learning methods for genomic prediction are implemented, including gradient boosted trees, random forests, stacked ensemble models, and multi-layer perceptrons. These prediction models can be evaluated via a collection of cross-validation schemes that mimic typical scenarios encountered by plant breeders working with MET experimental data in a user-friendly way. The package is fully open source and accessible on GitHub.

scholarly journals Comparison of Machine Learning Methods to Up-Scale Gross Primary Production

2021 ◽  
Vol 13 (13) ◽  
pp. 2448
Author(s):  
Tao Yu ◽  
Qiang Zhang ◽  
Rui Sun
Keyword(s):  
Machine Learning ◽  
Random Forest ◽  
Primary Production ◽  
Eddy Covariance ◽  
Carbon Flux ◽  
Gross Primary Production ◽  
Regional Scale ◽  
Learning Methods ◽  
Flux Tower ◽  
Machine Learning Methods

Eddy covariance observation is an applicable way to obtain accurate and continuous carbon flux at flux tower sites, while remote sensing technology could estimate carbon exchange and carbon storage at regional and global scales effectively. However, it is still challenging to up-scale the field-observed carbon flux to a regional scale, due to the heterogeneity and the unstable air conditions at the land surface. In this paper, gross primary production (GPP) from ground eddy covariance systems were up-scaled to a regional scale by using five machine learning methods (Cubist regression tree, random forest, support vector machine, artificial neural network, and deep belief network). Then, the up-scaled GPP were validated using GPP at flux tower sites, weighted GPP in the footprint, and MODIS GPP products. At last, the sensitivity of the input data (normalized difference vegetation index, fractional vegetation cover, shortwave radiation, relative humidity and air temperature) to the precision of up-scaled GPP was analyzed, and the uncertainty of the machine learning methods was discussed. The results of this paper indicated that machine learning methods had a great potential in up-scaling GPP at flux tower sites. The validation of up-scaled GPP, using five machine learning methods, demonstrated that up-scaled GPP using random forest obtained the highest accuracy.

Sign in / Sign up

Export Citation Format

Share Document