scholarly journals Machine Learning Techniques for Fine Dead Fuel Load Estimation Using Multi-Source Remote Sensing Data

2021 ◽  
Vol 13 (9) ◽  
pp. 1658
Author(s):  
Marina D’Este ◽  
Mario Elia ◽  
Vincenzo Giannico ◽  
Giuseppina Spano ◽  
Raffaele Lafortezza ◽  
...  
Keyword(s):  
Machine Learning ◽  
Remote Sensing ◽  
Predictive Power ◽  
Mean Squared Error ◽  
Remote Sensing Data ◽  
Machine Learning Techniques ◽  
Fuel Load ◽  
Load Estimation ◽  
Squared Error ◽  
Learning Techniques

Fine dead fuel load is one of the most significant components of wildfires without which ignition would fail. Several studies have previously investigated 1-h fuel load using standard fuel parameters or site-specific fuel parameters estimated ad hoc for the landscape. On the one hand, these methods have a large margin of error, while on the other their production times and costs are high. In response to this gap, a set of models was developed combining multi-source remote sensing data, field data and machine learning techniques to quantitatively estimate fine dead fuel load and understand its determining factors. Therefore, the objectives of the study were to: (1) estimate 1-h fuel loads using remote sensing predictors and machine learning techniques; (2) evaluate the performance of each machine learning technique compared to traditional linear regression models; (3) assess the importance of each remote sensing predictor; and (4) map the 1-h fuel load in a pilot area of the Apulia region (southern Italy). In pursuit of the above, fine dead fuel load estimation was performed by the integration of field inventory data (251 plots), Synthetic Aperture Radar (SAR, Sentinel-1), optical (Sentinel-2), and Light Detection and Ranging (LIDAR) data applying three different algorithms: Multiple Linear regression (MLR), Random Forest (RF), and Support Vector Machine (SVM). Model performances were evaluated using Root Mean Squared Error (RMSE), Mean Squared Error (MSE), the coefficient of determination (R2) and Pearson’s correlation coefficient (r). The results showed that RF (RMSE: 0.09; MSE: 0.01; r: 0.71; R2: 0.50) had more predictive power compared to the other models, while SVM (RMSE: 0.10; MSE: 0.01; r: 0.63; R2: 0.39) and MLR (RMSE: 0.11; MSE: 0.01; r: 0.63; R2: 0.40) showed similar performances. LIDAR variables (Canopy Height Model and Canopy cover) were more important in fuel estimation than optical and radar variables. In fact, the results highlighted a positive relationship between 1-h fuel load and the presence of the tree component. Conversely, the geomorphological variables appeared to have lower predictive power. Overall, the 1-h fuel load map developed by the RF model can be a valuable tool to support decision making and can be used in regional wildfire risk management.

Remote sensing data fusion and machine learning techniques for mineral exploration

2020 ◽  
Author(s):  
Priscilla Addison ◽  
Stephen Alwon ◽  
Alex Janevski ◽  
Kristopher Purens ◽  
Clyde Wheeler
Keyword(s):  
Machine Learning ◽  
Remote Sensing ◽  
Data Fusion ◽  
Mineral Exploration ◽  
Remote Sensing Data ◽  
Machine Learning Techniques ◽  
Sensing Data ◽  
Learning Techniques

scholarly journals Modeling the Relationship between Rice Yield and Climate Variables Using Statistical and Machine Learning Techniques

2021 ◽  
Vol 2021 ◽  
pp. 1-9
Author(s):  
Lasini Wickramasinghe ◽  
Rukmal Weliwatta ◽  
Piyal Ekanayake ◽  
Jeevani Jayasinghe
Keyword(s):  
Machine Learning ◽  
Mean Squared Error ◽  
Rice Yield ◽  
Machine Learning Techniques ◽  
Support Vector ◽  
Climatic Data ◽  
Climate Variables ◽  
Squared Error ◽  
Learning Techniques ◽  
The Relationship

This paper presents the application of a multiple number of statistical methods and machine learning techniques to model the relationship between rice yield and climate variables of a major region in Sri Lanka, which contributes significantly to the country’s paddy harvest. Rainfall, temperature (minimum and maximum), evaporation, average wind speed (morning and evening), and sunshine hours are the climatic factors considered for modeling. Rice harvest and yield data over the last three decades and monthly climatic data were used to develop the prediction model by applying artificial neural networks (ANNs), support vector machine regression (SVMR), multiple linear regression (MLR), Gaussian process regression (GPR), power regression (PR), and robust regression (RR). The performance of each model was assessed in terms of the mean squared error (MSE), correlation coefficient (R), mean absolute percentage error (MAPE), root mean squared error ratio (RSR), BIAS value, and the Nash number, and it was found that the GPR-based model is the most accurate among them. Climate data collected until early 2019 (Maha season of year 2018) were used to develop the model, and an independent validation was performed by applying data of the Yala season of year 2019. The developed model can be used to forecast the future rice yield with very high accuracy.

scholarly journals Graph input representations for machine learning applications in urban network analysis

2019 ◽  
pp. 239980831989259
Author(s):  
Alessio Pagani ◽  
Abhinav Mehrotra ◽  
Mirco Musolesi
Keyword(s):  
Machine Learning ◽  
New York ◽  
Mean Squared Error ◽  
Machine Learning Techniques ◽  
Urban Network ◽  
Urban Networks ◽  
Squared Error ◽  
Learning Techniques ◽  
Machine Learning Applications ◽  
The Impact

Understanding and learning the characteristics of network paths has been of particular interest for decades and has led to several successful applications. Such analysis becomes challenging for urban networks as their size and complexity are significantly higher compared to other networks. The state-of-the-art machine learning techniques allow us to detect hidden patterns and, thus, infer the features associated with them. However, very little is known about the impact on the performance of such predictive models by the use of different input representations. In this paper, we design and evaluate six different graph input representations (i.e. representations of the network paths), by considering the network’s topological and temporal characteristics, for being used as inputs for machine learning models to learn the behavior of urban network paths. The representations are validated and then tested with a real-world taxi journeys dataset predicting the tips of using a road network of New York. Our results demonstrate that the input representations that use temporal information help the model to achieve the highest accuracy (root mean-squared error of 1.42$).

Sign in / Sign up

Export Citation Format

Share Document