Search

Background: Accurate planning of the duration of stays at intensive care units is of utmost importance for resource planning. Currently, the discharge date used for resource management is calculated only at admission time and is called length of stay. However, the evolution of the treatment may be different from one patient to another, so a recalculation of the date of discharge should be performed, called days to discharge. The prediction of days to discharge during the stay at the ICU with statistical and data analysis methods has been poorly studied with low-quality results. This study aims to improve the prediction of the discharge date for any patient in intensive care units using artificial intelligence techniques. Methods: The paper proposes a hybrid method based on group-conditioned models obtained with machine learning techniques. Patients are grouped into three clusters based on an initial length of stay estimation. On each group (grouped by first days of stay), we calculate the group-conditioned length of stay value to know the predicted date of discharge, then, after a given number of days, another group-conditioned prediction model must be used to calculate the days to discharge in order to obtain a more accurate prediction of the number of remaining days. The study is performed with the eICU database, a public dataset of USA patients admitted to intensive care units between 2014 and 2015. Three machine learning methods (i.e., Random Forest, XGBoost, and lightGBM) are used to generate length of stay and days to discharge predictive models for each group. Results: Random Forest is the algorithm that obtains the best days to discharge predictors. The proposed hybrid method achieves a root mean square error (RMSE) and mean average error (MAE) below one day on

Globe-LFMC is an extensive global database of live fuel moisture content (LFMC) measured from 1,383 sampling sites in 11 countries: Argentina, Australia, China, France, Italy, Senegal, Spain, South Africa, Tunisia, United Kingdom and the United States of America. The database contains 161,717 individual records based on in situ destructive samples used to measure LFMC, representing the amount of water in plant leaves per unit of dry matter. The primary goal of the database is to calibrate and validate remote sensing algorithms used to predict LFMC. However, this database is also relevant for the calibration and validation of dynamic global vegetation models, eco-physiological models of plant water stress as well as understanding the physiological drivers of spatiotemporal variation in LFMC at local, regional and global scales. Globe-LFMC should be useful for studying LFMC trends in response to environmental change and LFMC influence on wildfire occurrence, wildfire behavior, and overall vegetation health.

The 3-D Radiative Transfer Model (RTM) FLIGHT can represent scattering in open forest or savannas featuring underlying bare soils. However, FLIGHT might not be suitable for multilayered tree-grass ecosystems (TGE), where a grass understory can dominate the reflectance factor (RF) dynamics due to strong seasonal variability and low tree fractional cover. To address this issue, we coupled FLIGHT with the 1-D RTM PROSAIL. The model is evaluated against spectral observations of proximal and remote sensing sensors: the ASD Fieldspec® 3 spectroradiometer, the Airborne Spectrographic Imager (CASI) and the MultiSpectral Instrument (MSI) onboard Sentinel-2. We tested the capability of both PROSAIL and PROSAIL+FLIGHT to reproduce the variability of different phenological stages determined by 16-year time series analysis of Moderate Resolution Imaging Spectroradiometer-Normalized Difference Vegetation Index (MODIS-NDVI). Then, we combined concomitant observations of biophysical variables and RF to test the capability of the models to reproduce observed RF. PROSAIL achieved a Relative Root Mean Square Error (RRMSE) between 6% to 32% at proximal sensing scale. PROSAIL+FLIGHT RRMSE ranged between 7% to 31% at remote sensing scales. RRMSE increased in periods when large fractions of standing dead material mixed with emergent green grasses —especially in autumn—; suggesting that the model cannot represent the spectral features of this material. PROSAIL+FLIGHT improves RF simulation especially in summer and at mid-high view angles.

The direct estimation of nitrogen (N) in fresh vegetation is challenging due to its weak influence on leaf reflectance and the overlaps with absorption features of other compounds. Different empirical modelsrelate in this work leaf nitrogen concentration ([N]Leaf) on Holm oak to leaf reflectance as well as derivedspectral indices such as normalized difference indices (NDIs), the three bands indices (TBIs) and indices previously used to predict leaf N and chlorophyll. The models were calibrated and assessed their accuracy, robustness and the strength of relationship when other biochemicals were considered. Red edge was the spectral region most strongly correlated with [N]Leaf, whereas most of the published spectral indexesdid not provide accurate estimations. NDIs and TBIs based models could achieve robust and acceptableaccuracies (TBI1310,1720,730 R2= 0.76, [0.64,0.86]; RMSE (%) = 9.36, [7.04,12.83]). These models sometimesincluded indices with bands close to absorption features of N bonds or nitrogenous compounds, but also of other biochemicals. Models were independently and inter-annually validated using the bootstrap method, which allowed discarding those models non-robust across different years. Partial correlationanalysis revealed that spectral estimators did not strongly respond to [N]Leaf but to other leaf variablessuch as chlorophyll and water, even if bands close to absorption features of N bonds or compounds werepresent in the models. © 2013 Elsevier B.V.

Contains fulltext : 158126.pdf (publisher's version ) (Closed access)

Contains fulltext : 91676.pdf (publisher's version ) (Closed access)