Integrating multiple factors to optimize watchtower deployment for wildfire detection.

Traditional human-vision-based watchtower systems are being gradually replaced by the machine-vision-based watchtower system. The visual range of machine-vision-based watchtower is smaller than the range of traditional human-vision-based watchtower, which has led to a sharp increase in the number of towers that should be deployed. Consequently, the overlapping area between watchtowers is larger and overlaps are more frequent than in conventional watchtower networks. This poses an urgent challenge: identifying the optimal locations for deployment. If the number of required watchtowers must be increased to extend the detection coverage, overlaps among watchtowers are inevitable and result in viewshed redundancy. However, this redundancy of the viewshed resources of the watchtowers has not been utilized in the design of fire detection systems. Moreover, fire ignition factors, such as climatic factors, fuels, and human behaviour, cause the fire occurrence risk to differ among forest areas. Thus, the fire risk map of the area should also be considered in watchtower deployment. A fire risk model is used as the first step in producing the fire risk map, which is used to propose a new watchtower deployment model for optimizing the watchtower system by integrating viewshed analysis, location allocation, and multi-coverage of the high-fire-risk area while considering the budget constraints for providing optimal coverage. We use a real dataset of a forest park to evaluate the applicability of our approach. The proposed approach is evaluated against the FV-NB (Full coVerage with No Budget constraint) algorithm and the XV-B (maXimum possible coVerage with a Budget constraint) algorithm in terms of performance. The evaluation results demonstrate that our approach realizes higher coverage gain and excellent multiple-coverage of the fire risk area by integrating the viewshed and the fire risk level into location allocation while satisfying requirements on the overall coverage and budget. The proposed approach is more suitable in the environments with moderate watchtower density, in which overlapping areas are frequent. It offers as much as 8.9-17.3% improvement of multiple-coverage of the high-fire-risk area.

[1]  D. Schmoldt,et al.  The Analytic Hierarchy Process in Natural Resource and Environmental Decision Making , 2001, Managing Forest Ecosystems.

[2]  Yunfei Liu,et al.  Anycast Routing Protocol for Forest Monitoring in Rechargeable Wireless Sensor Networks , 2013, Int. J. Distributed Sens. Networks.

[3]  M. Matin,et al.  Understanding forest fire patterns and risk in Nepal using remote sensing, geographic information system and historical fire data , 2017 .

[4]  Biswajeet Pradhan,et al.  Multi-hazard assessment modeling via multi-criteria analysis and GIS: a case study , 2019, Environmental Earth Sciences.

[5]  Ahmad A. A. Alkhatib.  A Review on Forest Fire Detection Techniques , 2014, Int. J. Distributed Sens. Networks.

[6]  Shitai Bao,et al.  Optimizing watchtower locations for forest fire monitoring using location models , 2015 .

[7]  Samir Khuller,et al.  The Budgeted Maximum Coverage Problem , 1999, Inf. Process. Lett..

[8]  Francisco Rego,et al.  Modelling the effects of distance on the probability of fire detection from lookouts , 2006 .

[9]  Muhammad Aamir,et al.  Towards Development of a Low Cost Early Fire Detection System Using Wireless Sensor Network and Machine Vision , 2017, Wirel. Pers. Commun..

[10]  David L. Martell,et al.  A Review of Recent Forest and Wildland Fire Management Decision Support Systems Research , 2015, Current Forestry Reports.

[11]  Mir Abolfazl Mostafavi,et al.  Wind effect on wildfire and simulation of its spread (case study: Siahkal forest in northern Iran). , 2014 .

[12]  Nhat-Duc Hoang,et al.  GIS-based spatial prediction of tropical forest fire danger using a new hybrid machine learning method , 2018, Ecol. Informatics.

[13]  Weibin You,et al.  Geographical information system-based forest fire risk assessment integrating national forest inventory data and analysis of its spatiotemporal variability , 2017 .

[14]  Mario Parise,et al.  Wildfire impacts on the processes that generate debris flows in burned watersheds , 2012, Natural Hazards.

[15]  Xiaojiang Chen,et al.  Maximizing throughput for low duty-cycled sensor networks , 2018, Comput. Networks.

[16]  Ana Daría Ruiz-González,et al.  Modeling and Mapping Forest Fire Occurrence from Aboveground Carbon Density in Mexico , 2019, Forests.

[17]  Reuven Cohen,et al.  The Generalized Maximum Coverage Problem , 2008, Inf. Process. Lett..

[18]  Haiqing Hu,et al.  Geographically Weighted Negative Binomial Regression Model Predicts Wildfire Occurrence in the Great Xing’an Mountains Better Than Negative Binomial Model , 2019, Forests.

[19]  Zhihua Liu,et al.  Relative effects of climatic and local factors on fire occurrence in boreal forest landscapes of northeastern China. , 2014, The Science of the total environment.

[20]  Sergi Costafreda-Aumedes,et al.  Human-caused fire occurrence modelling in perspective: a review , 2017 .

[21]  Hyunseung Choo,et al.  Towards broadcast redundancy minimization in duty-cycled wireless sensor networks , 2017, Int. J. Commun. Syst..

[22]  Lok Mani Sapkota,et al.  Fire Environment and Community-based Forest Fire Management in the Central Siwalik Region of Nepal , 2017 .

[23]  H. Hong,et al.  Predicting spatial patterns of wildfire susceptibility in the Huichang County, China: An integrated model to analysis of landscape indicators , 2019, Ecological Indicators.

[24]  David M. Szpakowski,et al.  A Review of the Applications of Remote Sensing in Fire Ecology , 2019, Remote. Sens..

[25]  Xuan Shi,et al.  Deriving a minimum set of viewpoints for maximum coverage over any given digital elevation model data , 2016, Int. J. Digit. Earth.

[26]  Luca Salvati,et al.  ‘Land of Fires’: Urban Growth, Economic Crisis, and Forest Fires in Attica, Greece , 2015 .

[27]  Guoliang Xing,et al.  Integrated coverage and connectivity configuration for energy conservation in sensor networks , 2005, TOSN.

[28]  L. Dimuccio,et al.  Regional forest-fire susceptibility analysis in central Portugal using a probabilistic ratings procedure and artificial neural network weights assignment , 2011 .

[29]  J. Díaz,et al.  Impact on mortality of biomass combustion from wildfires in Spain: A regional analysis. , 2018, The Science of the total environment.

[30]  E. S. Artsybashev.  Forest fires and their control. , 1983 .

[31]  Siren Lan,et al.  Visual sensitivity versus ecological sensitivity: An application of GIS in urban forest park planning , 2019, Urban Forestry & Urban Greening.

[32]  James Rodway,et al.  Harvesting-aware energy management for environmental monitoring WSN , 2016, 2016 IEEE 16th International Conference on Environment and Electrical Engineering (EEEIC).

[33]  Jin-Gu Kang,et al.  Energy-Efficient Forest Fire Prediction Model Based on Two-Stage Adaptive Duty-Cycled Hybrid X-MAC Protocol , 2018, Sensors.

[34]  Kurosh Madani,et al.  A human-like visual-attention-based artificial vision system for wildland firefighting assistance , 2017, Applied Intelligence.

[35]  Dieu Tien Bui,et al.  Genetic and firefly metaheuristic algorithms for an optimized neuro-fuzzy prediction modeling of wildfire probability. , 2019, Journal of environmental management.

[36]  Shitai Bao,et al.  3D locating system of observation tower with multiple constraints , 2011, International Conference on Photonics and Image in Agriculture Engineering.

[37]  Paul E. Gessler,et al.  Soil-Landscape Modelling and Spatial Prediction of Soil Attributes , 1995, Int. J. Geogr. Inf. Sci..

[38]  Young-Hoon Kim,et al.  Exploring multiple viewshed analysis using terrain features and optimisation techniques , 2004, Comput. Geosci..

[39]  Futao Guo,et al.  What drives forest fire in Fujian, China? Evidence from logistic regression and Random Forests , 2016 .

[40]  Hamid Reza Pourghasemi,et al.  A comparative assessment of prediction capabilities of modified analytical hierarchy process (M-AHP) and Mamdani fuzzy logic models using Netcad-GIS for forest fire susceptibility mapping , 2016 .

[41]  Zohre Sadat Pourtaghi,et al.  Investigation of general indicators influencing on forest fire and its susceptibility modeling using different data mining techniques , 2016 .

[42]  Mehmet Cetin,et al.  Visibility analysis of fire lookout towers in the Boyabat State Forest Enterprise in Turkey , 2017, Environmental Monitoring and Assessment.

[43]  J. Beverly,et al.  Burn probability simulation and subsequent wildland fire activity in Alberta, Canada – Implications for risk assessment and strategic planning , 2019, Forest Ecology and Management.

[44]  Nilton Cesar Fiedler,et al.  Applying GIS to develop a model for forest fire risk: A case study in Espírito Santo, Brazil. , 2016, Journal of environmental management.

[45]  J. A. Schell,et al.  Monitoring vegetation systems in the great plains with ERTS , 1973 .

[46]  H. Pourghasemi.  GIS-based forest fire susceptibility mapping in Iran: a comparison between evidential belief function and binary logistic regression models , 2016 .

[47]  Shanti Bhushan,et al.  Wildfire risk prediction in Southeastern Mississippi using population interaction , 2013 .

[48]  Daniel Joly,et al.  Integrated GIS software for computing landscape visibility metrics , 2018, Trans. GIS.

[49]  Yunfei Liu,et al.  Data Aggregation Routing for Rechargeable Wireless Sensor Networks in Forest Monitoring , 2014, Wirel. Pers. Commun..

[50]  Tufan Demirel,et al.  Visibility Analysis of Fire Watchtowers Using GIS; A Case Study in Dalaman State Forest Enterprise , 2017 .

[51]  Ronie Silva Juvanhol,et al.  GIS applied to location of fires detection towers in domain area of tropical forest. , 2016, The Science of the total environment.

[52]  J. M. Gleriani,et al.  Potentials and limitations of remote fire monitoring in protected areas. , 2018, The Science of the total environment.

[53]  Piermaria Corona,et al.  The background context matters: Local-scale socioeconomic conditions and the spatial distribution of wildfires in Italy. , 2019, The Science of the total environment.

[54]  Calogero Schillaci,et al.  Terrain analysis and landform recognition , 2015 .

[55]  A. Zhu,et al.  Applying genetic algorithms to set the optimal combination of forest fire related variables and model forest fire susceptibility based on data mining models. The case of Dayu County, China. , 2018, The Science of the total environment.

[56]  Thia Kirubarajan,et al.  Terrain-influenced incremental watchtower expansion for wildfire detection. , 2019, The Science of the total environment.

[57]  L. Longoni,et al.  Wildfire Impacts on Slope Stability Triggering in Mountain Areas , 2019, Geosciences.

[58]  Jennifer K. Balch,et al.  Human-started wildfires expand the fire niche across the United States , 2017, Proceedings of the National Academy of Sciences.

[59]  Evan R. DeLancey,et al.  The spatially varying influence of humans on fire probability in North America , 2016 .

[60]  Tymon Zielinski,et al.  Impact of wild forest fires in Eastern Europe on aerosol composition and particle optical properties , 2016 .

[61]  Hai Liu,et al.  Maximal lifetime scheduling for K to 1 sensor-target surveillance networks , 2006, Comput. Networks.

[62]  M. Amraoui,et al.  Drought in Portugal: Current regime, comparison of indices and impacts on extreme wildfires. , 2019, The Science of the total environment.

[63]  Andrew L. Sullivan,et al.  Field evaluation of two image-based wildland fire detection systems , 2012 .

[64]  Matthew P. Thompson,et al.  Designing Operationally Relevant Daily Large Fire Containment Strategies Using Risk Assessment Results , 2019, Forests.