Testing the performance of a forest ecosystem model (FORECAST) against 29 years of field data in a Pseudotsuga menziesii plantation

2007 ◽  
Vol 37 (10) ◽  
pp. 1808-1820 ◽  
Author(s):  
Juan A. Blanco ◽  
Brad Seely ◽  
Clive Welham ◽  
J. P. (Hamish) Kimmins ◽  
Tanya M. Seebacher
Keyword(s):  
Pseudotsuga Menziesii ◽  
Forest Ecosystem ◽  
Model Performance ◽  
Field Measurements ◽  
Stem Density ◽  
Model Forecast ◽  
Regional Data ◽  
Data Set ◽  
Site Specific ◽  
Specific Data

The ability of the forest ecosystem management model FORECAST to project a 29-year record of stand response to factorial thinning and fertilization treatments in a Douglas-fir ( Pseudotsuga menziesii (Mirb.) Franco) plantation at Shawnigan Lake (Vancouver Island, British Columbia, Canada) was assessed. Model performance was evaluated firstly using for calibration a regional data set and secondly with site-specific data from control plots. Model output was compared against field measurements of height, diameter, stem density, component biomass (aboveground), and litterfall rates and estimates of nutrient uptake, foliar N efficiency, and understory vegetation biomass. When calibrated with regional data, results from graphical comparisons, three measures of goodness-of-fit, and equivalence testing demonstrated that FORECAST can produce predictions of good to moderate accuracy depending on the variable of interest. Model performance was generally better when compared with field measurements (e.g., top height, diameter at breast height, and stem density) as opposed to outputs derived from allometric and volume equations. Use of site-specific data to calibrate the model always improved performance, although improvements were modest for most variables, with the exception of branch and foliage biomass. The benefits of site-specific calibration, however, should be weighed against the costs of obtaining such data. The intended use of the model will likely determine the level of effort expended in its calibration.

scholarly journals DeepPaSTL: Spatio-Temporal Deep Learning Methods for Predicting Long-Term Pasture Terrains Using Synthetic Datasets

Agronomy ◽  
2021 ◽  
Vol 11 (11) ◽  
pp. 2245
Author(s):  
Murtaza Rangwala ◽  
Jun Liu ◽  
Kulbir Singh Ahluwalia ◽  
Shayan Ghajar ◽  
Harnaik Singh Dhami ◽  
...  
Keyword(s):  
Deep Learning ◽  
Growth Dynamics ◽  
Field Measurements ◽  
Soil Condition ◽  
Climatic Conditions ◽  
Site Specific ◽  
Specific Data ◽  
Spatio Temporal ◽  
Synthetic Datasets ◽  
Prediction Systems

Effective management of dairy farms requires an accurate prediction of pasture biomass. Generally, estimation of pasture biomass requires site-specific data, or often perfect world assumptions to model prediction systems when field measurements or other sensory inputs are unavailable. However, for small enterprises, regular measurements of site-specific data are often inconceivable. In this study, we approach the estimation of pasture biomass by predicting sward heights across the field. A convolution based sequential architecture is proposed for pasture height predictions using deep learning. We develop a process to create synthetic datasets that simulate the evolution of pasture growth over a period of 30 years. The deep learning based pasture prediction model (DeepPaSTL) is trained on this dataset while learning the spatiotemporal characteristics of pasture growth. The architecture purely learns from the trends in pasture growth through available spatial measurements and is agnostic to any site-specific data, or climatic conditions, such as temperature, precipitation, or soil condition. Our model performs within a 12% error margin even during the periods with the largest pasture growth dynamics. The study demonstrates the potential scalability of the architecture to predict any pasture size through a quantization approach during prediction. Results suggest that the DeepPaSTL model represents a useful tool for predicting pasture growth both for short and long horizon predictions, even with missing or irregular historical measurements.

Generalized biomass estimation equations for Betulapapyrifera Marsh.

1981 ◽  
Vol 11 (4) ◽  
pp. 837-840 ◽  
Author(s):  
Mark D. C. Schmitt ◽  
D. F. Grigal
Keyword(s):  
New Hampshire ◽  
Aboveground Biomass ◽  
Biomass Estimation ◽  
Mean Square ◽  
Data Set ◽  
Site Specific ◽  
Specific Data ◽  
Independent Variables ◽  
Breast Height ◽  
Estimation Equations

Aboveground biomass estimation equations were developed and compared for several components of Betulapapyrifera Marsh, trees using diameter at breast height (dbh) alone or dbh and height as independent variables. The data upon which the equations are based were collected by a number of different investigators working in Minnesota, Wisconsin, New Hampshire, and several sites in Maine and New Brunswick. Coefficients of determination ranged from 0.82 to 0.99, with higher values for bole than for crown components. The root mean-square deviation of the observations from the model was in the range 1 – 10 kg for any component. The largest trees in the data set (ca. 30 cm dbh) had total aboveground biomass of about 540 kg. In the absence of site-specific data, these equations provide acceptable estimates of biomass for B. papyrifera.

Application of private site-specific data to regional evaluation of earthquake and faulting potential in Southern California

1982 ◽  
Author(s):  
D.L. Lamar ◽  
J. L. Smith ◽  
J. W. La Violette ◽  
K. Custis ◽  
P.J. Scrivner
Keyword(s):  
Southern California ◽  
Site Specific ◽  
Specific Data

scholarly journals Data Augmentation Using Generative Adversarial Network for Automatic Machine Fault Detection Based on Vibration Signals

2021 ◽  
Vol 11 (5) ◽  
pp. 2166
Author(s):  
Van Bui ◽  
Tung Lam Pham ◽  
Huy Nguyen ◽  
Yeong Min Jang
Keyword(s):  
Fault Detection ◽  
Data Augmentation ◽  
Model Performance ◽  
Original Data ◽  
Fault Classification ◽  
Training Process ◽  
Generative Adversarial Network ◽  
Data Set ◽  
Adversarial Network ◽  
Machine Fault

In the last decade, predictive maintenance has attracted a lot of attention in industrial factories because of its wide use of the Internet of Things and artificial intelligence algorithms for data management. However, in the early phases where the abnormal and faulty machines rarely appeared in factories, there were limited sets of machine fault samples. With limited fault samples, it is difficult to perform a training process for fault classification due to the imbalance of input data. Therefore, data augmentation was required to increase the accuracy of the learning model. However, there were limited methods to generate and evaluate the data applied for data analysis. In this paper, we introduce a method of using the generative adversarial network as the fault signal augmentation method to enrich the dataset. The enhanced data set could increase the accuracy of the machine fault detection model in the training process. We also performed fault detection using a variety of preprocessing approaches and classified the models to evaluate the similarities between the generated data and authentic data. The generated fault data has high similarity with the original data and it significantly improves the accuracy of the model. The accuracy of fault machine detection reaches 99.41% with 20% original fault machine data set and 93.1% with 0% original fault machine data set (only use generate data only). Based on this, we concluded that the generated data could be used to mix with original data and improve the model performance.

scholarly journals Facing the needs for clean bicycle data – a bicycle-specific approach of GPS data processing

2021 ◽  
Vol 13 (1) ◽  
Author(s):  
Sven Lißner ◽  
Stefan Huber
Keyword(s):  
Data Processing ◽  
Gps Data ◽  
Data Set ◽  
Specific Data ◽  
Driving Mode ◽  
Mode Detection ◽  
Current State ◽  
Mode Recognition ◽  
Recorded Data ◽  
Gps Tracks

Abstract Background GPS-based cycling data are increasingly available for traffic planning these days. However, the recorded data often contain more information than simply bicycle trips. GPS tracks resulting from tracking while using other modes of transport than bike or long periods at working locations while people are still tracking are only some examples. Thus, collected bicycle GPS data need to be processed adequately to use them for transportation planning. Results The article presents a multi-level approach towards bicycle-specific data processing. The data processing model contains different steps of processing (data filtering, smoothing, trip segmentation, transport mode recognition, driving mode detection) to finally obtain a correct data set that contains bicycle trips, only. The validation reveals a sound accuracy of the model at its’ current state (82–88%).

scholarly journals Hospital acquired pressure injury prediction in surgical critical care patients

2021 ◽  
Vol 21 (1) ◽  
Author(s):  
Jenny Alderden ◽  
Kathryn P. Drake ◽  
Andrew Wilson ◽  
Jonathan Dimas ◽  
Mollie R. Cummins ◽  
...  
Keyword(s):  
Risk Assessment ◽  
Model Performance ◽  
Routine Care ◽  
Predictor Variables ◽  
Classification Algorithms ◽  
Data Set ◽  
Icu Patients ◽  
Pressure Injury ◽  
Surgical Icu ◽  
Hospital Acquired

Abstract Background Hospital-acquired pressure injuries (HAPrIs) are areas of damage to the skin occurring among 5–10% of surgical intensive care unit (ICU) patients. HAPrIs are mostly preventable; however, prevention may require measures not feasible for every patient because of the cost or intensity of nursing care. Therefore, recommended standards of practice include HAPrI risk assessment at routine intervals. However, no HAPrI risk-prediction tools demonstrate adequate predictive validity in the ICU population. The purpose of the current study was to develop and compare models predicting HAPrIs among surgical ICU patients using electronic health record (EHR) data. Methods In this retrospective cohort study, we obtained data for patients admitted to the surgical ICU or cardiovascular surgical ICU between 2014 and 2018 via query of our institution's EHR. We developed predictive models utilizing three sets of variables: (1) variables obtained during routine care + the Braden Scale (a pressure-injury risk-assessment scale); (2) routine care only; and (3) a parsimonious set of five routine-care variables chosen based on availability from an EHR and data warehouse perspective. Aiming to select the best model for predicting HAPrIs, we split each data set into standard 80:20 train:test sets and applied five classification algorithms. We performed this process on each of the three data sets, evaluating model performance based on continuous performance on the receiver operating characteristic curve and the F1 score. Results Among 5,101 patients included in analysis, 333 (6.5%) developed a HAPrI. F1 scores of the five classification algorithms proved to be a valuable evaluation metric for model performance considering the class imbalance. Models developed with the parsimonious data set had comparable F1 scores to those developed with the larger set of predictor variables. Conclusions Results from this study show the feasibility of using EHR data for accurately predicting HAPrIs and that good performance can be found with a small group of easily accessible predictor variables. Future study is needed to test the models in an external sample.

scholarly journals Development of a semi-parametric PAR (Photosynthetically Active Radiation) partitioning model for the United States, version 1.0

2014 ◽  
Vol 7 (5) ◽  
pp. 2477-2484 ◽  
Author(s):  
J. C. Kathilankal ◽  
T. L. O'Halloran ◽  
A. Schmidt ◽  
C. V. Hanson ◽  
B. E. Law
Keyword(s):  
United States ◽  
Elevation Angle ◽  
Model Performance ◽  
Diffuse Radiation ◽  
The United States ◽  
Polynomial Model ◽  
Coefficient Of Determination ◽  
Data Set ◽  
Cubic Polynomial ◽  
Solar Elevation Angle

Abstract. A semi-parametric PAR diffuse radiation model was developed using commonly measured climatic variables from 108 site-years of data from 17 AmeriFlux sites. The model has a logistic form and improves upon previous efforts using a larger data set and physically viable climate variables as predictors, including relative humidity, clearness index, surface albedo and solar elevation angle. Model performance was evaluated by comparison with a simple cubic polynomial model developed for the PAR spectral range. The logistic model outperformed the polynomial model with an improved coefficient of determination and slope relative to measured data (logistic: R2 = 0.76; slope = 0.76; cubic: R2 = 0.73; slope = 0.72), making this the most robust PAR-partitioning model for the United States currently available.

Sign in / Sign up

Export Citation Format

Share Document