Previous wildfire risk assessments have problems such as subjectivity of weight allocation and the linearization of statistical models, resulting in generally low robustness and low generalization ability of fire risk assessment models. Therefore, in this paper, we explored the potential of integration machine learning algorithms to build wildfire risk assessment models. Based on analyzing fire data’s spatial and temporal distribution, we selected 10 triggering factors of topography, meteorology, vegetation, and human activities, using frequency ratio (FR) to provide uniform data representation of triggering factors. Next, we used the Bayesian optimization (BO) algorithm to perform hyperparametric optimization solutions for various machine learning models: support vector machine (SVM), random forest (RF), and extreme gradient boosting (XGBoost). Finally, we constructed an integration machine learning algorithm to acquire a fire risk grading map and the importance evaluation corresponding to each triggering factor. For validation purposes, we selected Liangshan Prefecture in Sichuan Province as the specific study area and obtained MCD64A1 burned area product to extract the extent of burned areas in Liangshan Prefecture from 2011 to 2020. The accuracy, kappa coefficient, and area under curve (AUC) were then applied to assess the predictive power and consistency of the fire risk classification maps. The experimental analysis showed that among the three models, FR-BO-XGBoost had the best performance in wildfire risk assessment in the Liangshan region (AUC = 0.887), followed by FR-BO-RF (AUC = 0.876) and FR-BO-SVM (AUC = 0.820). The feature importance result indicated that the study area’s most significant effects on wildfires were precipitation, NDVI, land cover, and maximum temperature. The proposed method avoided the subjective weighting and model linearization problems. Compared with the previous methods, it automatically acquired the importance of the triggering factors to the wildfire, which had certain advantages in wildfire risk assessment, and was worthy of further promotion.
Vegetation net primary productivity (VNPP) is the main factor in ecosystem carbon sink function and regulation of environmental processes. However, NPP data products have data missing in some areas, which affects the availability and overall accuracy level of data. Therefore, we adopted the Factor Analysis Backpropagation neural network model (FA-BP model) to acquire a high-accuracy and high-reliability NPP result without missing or empty areas by using a series of easily accessible datasets, such as meteorological data and remote sensing data. We selected the western Sichuan region as the study area and carried out a VNPP time series estimation from 2000 to 2016. Comparative simulations also verify the accuracy of the time series estimation results: The Pearson correlation r of VNPP prediction results ranged from 0.807 to 0.917, the mean absolute error ranged from 29.1 to 38.9, the root mean square error was between 37.3 and 51.8, and the mean relative error varies from 0.10 to 0.14. Further analysis shows that the spatial pattern of estimated VNPP during the past 17 years in western Sichuan shows a decreasing trend from southeast to northwest. Besides, the VNPP time series is generally on an upward trend in this period. The increasing and decreasing areas of VNPP values in the study area accounted for 81.42% and 18.58%, respectively. Moreover, we find that temperature dominates the change of VNPP in the whole western Sichuan region. The data processing method and experimental results presented in this paper can provide a reference for accurately acquiring VNPP and related studies on natural resources and climate change.
Compared with previous snow depth monitoring methods, global navigation satellite system-interferometric reflectometry (GNSS-IR) technology has the advantage of obtaining continuous daily observation data, and has great application potential. However, since GNSS satellites are in motion, their position in the sky is constantly varying, and the Fresnel reflection areas about the receiver in different periods alter accordingly. As a result, the retrieving results obtained from different GNSS satellites, and data sets collected in different periods, fluctuate considerably, making the traditional single-satellite-based GNSS-IR retrieving method have limitations in accuracy and reliability. Therefore, this paper proposed a novel GNSS-IR signal-to-noise ratio (SNR) retrieving snow depth method for fusing the available GNSS-IR observations to obtain an accurate and reliable result. We established the retrieval model based on the backpropagation algorithm, which makes full use of the back propagation (BP) neural network’s self-learning and self-adaptive capability to exploit the degree of contribution of different satellites to the final results. Then, the SNR observations of the global positioning system (GPS) L1 carrier from the Plate Boundary Observation (PBO) site P351 were collected to experiment for validation purposes. For all available GPS L1 carrier data, the snow depth values retrieved for each satellite were first obtained by the existing single-satellite-based GNSS-IR retrieval method. Then, four groups of comparison results were acquired, based on the multiple linear regression model, random forest model, mean fusion model, and the proposed BP neural network model, respectively. Taking the snow depth in-situ data provided by snow telemetry (SNOTEL) as a reference, the root mean squared error (RMSE) and mean absolute error (MAE) of the proposed solution are 0.0297 m and 0.0219 m, respectively. Furthermore, the retrieving results are highly consistent with the measured data, and the correlation coefficient is 0.9407.
scite is a Brooklyn-based organization that helps researchers better discover and understand research articles through Smart Citations–citations that display the context of the citation and describe whether the article provides supporting or contrasting evidence. scite is used by students and researchers from around the world and is funded in part by the National Science Foundation and the National Institute on Drug Abuse of the National Institutes of Health.
hi@scite.ai
10624 S. Eastern Ave., Ste. A-614
Henderson, NV 89052, USA
Copyright © 2024 scite LLC. All rights reserved.
Made with 💙 for researchers
Part of the Research Solutions Family.