Prediction of Peat Forest Fires Using Wavelet and Backpropagation

One of the causes of smog as well as climate damage, particularly in Palangka Raya, Center Kalimantan, are peat forest fires. There are a lot of losses inflicted by the smog including the increasing number of people who suffer respiratory infection (ARI) due to polluted air and any other related aspects. Peat fires are problematic to overcome because the locations of fires are difficult to be accessed. This paper focuses on building the system to predict the distribution of peat forest fire hotspots by utilizing satellite imagery. In designing the system for predicting the fire hotspots distribution, wavelet orthogonal was used as the initial processing of mapping the distribution of peat forest fire hotspots. Meanwhile, backpropagation method was used to identify the fire hotspot distribution patterns of peat forest fire in this system. From the result of the data tested which had been done for predicting the peat forest fire hotspots, the decomposition image obtained using Haar wavelet had the highest percentage of accuracy to recognize the fire hotspots, which is 90%. The recency of this system was its ability to predict the peat forest fire hotspots distribution which can be used as peat forest fires prevention, especially in Palangka Raya, Central Kalimantan.

Download Full-text

Distribution Pattern of Children with Acute Respiratory Infection during Forest fire at Central Kalimantan Indonesia

Bangladesh Journal of Medical Science ◽

10.3329/bjms.v21i1.56345 ◽

2022 ◽

Vol 21 (1) ◽

pp. 171-174

Author(s):

Yoni Astuti ◽

Iman Permana ◽

Bayu Ramadhan ◽

Rahmawati Hussein

Keyword(s):

Distribution Pattern ◽

Respiratory Infection ◽

Forest Fire ◽

Acute Respiratory Infection ◽

Global Climate ◽

Medical Science ◽

Central Kalimantan ◽

Public Health Office ◽

Pm 10 ◽

The Impact

Over the past 30 years, forest fire has been one of main ecological issues in Indonesia. Human-caused deforestation was accused to be the reason behind this matter, apart from the drastic changing in global climate. Palangkaraya is one of the citiesaffected by haze of the forest fire in 2015; considered to be the worst year of forest fire with the value of PM10 was above the normal threshold. As the impact to the community wellbeing, the prevalence of acute respiratory infection (ARI) in October 2015was increasing especially in children. The research aimed to analyse the spatial distribution of children with ARI in October 2015 at Palangkaraya City. Data onARI number were collected from Primary Care under Public Health Office of Palangkaraya City. The PM 10 value was collected bythe Environmental Agency of Palangkaraya City. The spatial analyse method was conducted using theAverage Nearest Neighbour (ANN) method. The result shows that the number of ANN ratio is 0.761801. It means that the distribution pattern of children with ARI in Central Kalimantan during the forest fire in October 2015 was in cluster form. Bangladesh Journal of Medical Science Vol. 21(1) 2022 Page : 171-174

Download Full-text

Engaging Palm Oil and Hot Spot Area to Mitigate Forest Fires

BIO Web of Conferences ◽

10.1051/bioconf/20202001003 ◽

2020 ◽

Vol 20 ◽

pp. 01003

Author(s):

Ariesta Lestari ◽

Katriani Puspita Ayu

Keyword(s):

Forest Fire ◽

Palm Oil ◽

Forest Fires ◽

Hot Spot ◽

Fire Risk ◽

Risk Zone ◽

Central Kalimantan ◽

Forest Clearing ◽

Spot Area ◽

Forest Fire Management

Forest fire is one of environmental problem happens in Central Kalimantan. The fire does not only damage the forest ecosystem and biodiversity but also threaten the health and socio-economic of local people. Forest fire in Central Kalimantan is widely known as human-made, such as the process of shifting cultivation and land clearing. The expansion of forest into palm oil plantation is often blamed as the cause of forest fire since the forest clearing involves a massive amount of fires. Therefore, this study aims to explore whether the existence of palm oil cultivation contributes to the occurrence of forest fires. We used satellite imagery of hotspot, and overlay it with the land use data to generate the fire risk zone map using geographic information system (GIS) method. Through the map, the risk of fire can be monitored in advance to help the fire authority provide the act of mitigation. The result of this study suggested that risk mapping is vital for forest fire management to mitigate the spread of forest fire. The region to be fire-prone within the palm oil cultivation is suggested to form a preventive act through active forest-fires monitoring. In sum, this study is expected to provide a map of forest fires' risk around the cultivation area, mainly palm oil plantation, and help the fire authorities as well as stakeholders to identify the risk zone for fires prevention in the future.

Download Full-text

PEMANFAATAN DATA SATELIT HIMAWARI 8 UNTUK MENDETEKSI SEBARAN ASAP: STUDI KASUS DI KALIMANTAN DAN SUMATERA TANGGAL 8 DAN 9 SEPTEMBER 2015

SPEKTRA Jurnal Fisika dan Aplikasinya ◽

10.21009/spektra.022.10 ◽

2017 ◽

Vol 2 (2) ◽

pp. 157

Author(s):

Ayu Vista Wulandari ◽

Ni Kadek Trisna Dewi ◽

Wishnu Agum Swastiko

Keyword(s):

Satellite Imagery ◽

Forest Fire ◽

Forest Fires ◽

Near Infrared ◽

Negative Impact ◽

Distribution Data ◽

Observation Data ◽

False Color ◽

Negative Impacts ◽

Infrared Channel

The forest fires that occurred in the entire month of September 2015 was quite considerably disturbing many public activities in Borneo and Sumatera. The smoke which is caused by forest fire has negative impact for the surrounding environments, one of them is reducing horizontal visibility. Meteorological stations in Borneo and Sumatra recorded the lowest visibility occurred on September, 8th and 9th 2015 at average range was 100 m. Based on information of BMKG (Indonesian Agency of Meteorological, Climatological and Geophysics) noted that during the month of September 2015 there was a distribution of hotspots which indicates the occurrence of forest fire cases. This research is aimed to determine the potential of distribution of smoke by satellite imagery of Himawari 8 to reduce its negative impacts. By using this method that is by comparing the hotspot distribution data from BMKG with false color RGB image product (1 visible channel and 2 near infrared channel) along with trajectory of smoke’s distribution by utilizing application of GMSLPD SATAID. The distribution of smoke can be seen as an image with the brownish pattern which partially covered the area of Borneo and Sumatera. The result showed that the smoke’s distribution by the result of RGB imagery well-matched enough with the hotspot’s distribution data from BMKG, which the smoke almost covered most area of the western of Sumatera and center of Borneo. In this case also supported by the trajectory of smoke’s distribution which is derived from southeast-south and spread to the northwest-north in the researches area. By using the observation data from chosen meteorological stations showed a similar result with the above method. Thus, it can be assumed that by using satellite imagery of Himawari 8 is quite capable to discover smoke’s distribution caused by forest fires case. Keywords: Smoke, Satellite, Himawari 8, SATAID.

Download Full-text

Spatial Distribution Patterns Analysis of Hotspot in Central Kalimantan using FIMRS MODIS Data

Jurnal Geografi Lingkungan Tropik ◽

10.7454/jglitrop.v4i1.74 ◽

2020 ◽

Vol 4 (1) ◽

Cited By ~ 1

Author(s):

Adisty Pratamasari ◽

Ni Ketut Feny Permatasari ◽

Tia Pramudiyasari ◽

Masita Dwi Mandini Manessa ◽

Supriatna Supriatna

Keyword(s):

Remote Sensing ◽

Spatial Distribution ◽

Correlation Analysis ◽

Spatial Pattern ◽

Forest Fires ◽

Nearest Neighbor ◽

Kernel Density ◽

Distribution Patterns ◽

Central Kalimantan ◽

Noaa Avhrr

One of the ways to observe the hotspot created by forest fires in Indonesia is through Remote sensing imagery, such as MODIS, NOAA AVHRR, etc. Central Kalimantan is one of the areas in Indonesia with the highest hotspot data. In this research, MODIS FIRMS hotspot data in Central Kalimantan collected from 2017 – 2019, covering 13 districts: South Barito, East Barito, North Barito, Mount Mas, Kapuas, Katingan, Palangkaraya City, West Kotawaringin, East Kotawaringin, Lamandau, Murung Raya, Pulang Pisau, Seruyan, and Sukamara. That is four aspects that this research evaluated: 1) evaluating the spatial pattern using the Nearest Neighbor Analysis (NNA); 2) evaluate the hotspot density appearance using Kernel Density; and 3) correlation analysis between rainfall data and MODIS FIRMS. As a result, the hotspot in Central Kalimantan shows a clustered pattern. While the natural breaks KDE algorithm shows the most relevant result to represent the hotspot distribution. Finally, the hotspot is low correlated with rainfall; however, is see that most of the hotspot (~90%) appeared in low rainfall month (less than 3000 mm/month).Keywords: Forest fire, Hotspot, NNA, Kernel density, Central Kalimantan

Download Full-text

Mapping the Location of Wildfires in Alaskan Boreal Forests Using AVHRR Imagery

International Journal of Wildland Fire ◽

10.1071/wf9950055 ◽

1995 ◽

Vol 5 (2) ◽

pp. 55 ◽

Cited By ~ 11

Author(s):

NHF French ◽

ES Kasischke ◽

LL Bourgeau-Chavez ◽

D Berry

Keyword(s):

Boreal Forest ◽

Satellite Imagery ◽

Forest Fire ◽

Forest Fires ◽

Boreal Forests ◽

Fire Scars ◽

Area Burned ◽

Avhrr Data ◽

Avhrr Imagery

The results of a study using satellite imagery to map boreal forest fires in Alaska in 1990 and 1991 are presented. Composite AVHRR data detected more than 80% of fires greater than 2000 ha in size. Additionally, using a two season method, 78% of the area of all boreal forest fires in Alaska was mapped. This technique is considered to be an accurate way to detect forest fire scars and estimate area burned throughout the boreal forests, and could be very important in those regions where wildfire data are presently difficult or impossible to gather.

Download Full-text

Faktor-Faktor Yang Mempengaruhi Kebakaran Hutan Di Indonesia Dan Implikasi Kebijakannya

Jurnal Sylva Lestari ◽

10.23960/jsl13103-112 ◽

2015 ◽

Vol 3 (1) ◽

pp. 103 ◽

Cited By ~ 2

Author(s):

S. Andy Cahyono ◽

Sofyan P Warsito ◽

Wahyu Andayani ◽

Dwidjono H Darwanto

Keyword(s):

Forest Fire ◽

Forest Fires ◽

Time Series Data ◽

Series Data ◽

Factors Affecting ◽

Export Prices ◽

Preventive Effort ◽

Global Concern ◽

Peat Fires ◽

Early Indication

ABSTRACT Forest fire is one of the crucial environmental and forestry issues as well as local and global concern. The longstanding efforts have been conducted to overcome this problem, but the success was relatively low. This study aims to determine the factors that affect the extent of forest and peat fires in Indonesia. The analysis of forest fires was carried out on three major islands, i.e. Sumatra, Kalimantan and Papua using time series data from 1969 to 2012. The data were analyzed using econometric models. The results indicated that the factors affecting the forest and peat fires included the price of logs, export prices of CPO, el nino, budget of the Ministry of Forestry, the economic crisis and the number of hotspots. The identified determinant which has a major impact on the extent of forest and peat fires is the number of hotspots. Controlling the number of hotspots significantly reduced the magnitude of forest fires. For that reason, there is a need for a paradigm shift in the control of forest fires from forest fire fighting activities into preventive effort by reducing the number or preventing the occurrence of hotspots as an early indication of a forest fire. Keywords: forest fires, hotspots, prevention

Download Full-text

A Collaborative Region Detection and Grading Framework for Forest Fire Smoke Using Weakly Supervised Fine Segmentation and Lightweight Faster-RCNN

Forests ◽

10.3390/f12060768 ◽

2021 ◽

Vol 12 (6) ◽

pp. 768

Author(s):

Jin Pan ◽

Xiaoming Ou ◽

Liang Xu

Keyword(s):

Forest Fire ◽

Forest Fires ◽

Learning Strategy ◽

Early Stage ◽

Fire Detection ◽

Surveillance Systems ◽

Region Detection ◽

Decision Network ◽

Fire Smoke ◽

Weakly Supervised

Forest fires are serious disasters that affect countries all over the world. With the progress of image processing, numerous image-based surveillance systems for fires have been installed in forests. The rapid and accurate detection and grading of fire smoke can provide useful information, which helps humans to quickly control and reduce forest losses. Currently, convolutional neural networks (CNN) have yielded excellent performance in image recognition. Previous studies mostly paid attention to CNN-based image classification for fire detection. However, the research of CNN-based region detection and grading of fire is extremely scarce due to a challenging task which locates and segments fire regions using image-level annotations instead of inaccessible pixel-level labels. This paper presents a novel collaborative region detection and grading framework for fire smoke using a weakly supervised fine segmentation and a lightweight Faster R-CNN. The multi-task framework can simultaneously implement the early-stage alarm, region detection, classification, and grading of fire smoke. To provide an accurate segmentation on image-level, we propose the weakly supervised fine segmentation method, which consists of a segmentation network and a decision network. We aggregate image-level information, instead of expensive pixel-level labels, from all training images into the segmentation network, which simultaneously locates and segments fire smoke regions. To train the segmentation network using only image-level annotations, we propose a two-stage weakly supervised learning strategy, in which a novel weakly supervised loss is proposed to roughly detect the region of fire smoke, and a new region-refining segmentation algorithm is further used to accurately identify this region. The decision network incorporating a residual spatial attention module is utilized to predict the category of forest fire smoke. To reduce the complexity of the Faster R-CNN, we first introduced a knowledge distillation technique to compress the structure of this model. To grade forest fire smoke, we used a 3-input/1-output fuzzy system to evaluate the severity level. We evaluated the proposed approach using a developed fire smoke dataset, which included five different scenes varying by the fire smoke level. The proposed method exhibited competitive performance compared to state-of-the-art methods.

Download Full-text

Short-Term Effects of Fire Severity on Vegetation Based on Sentinel-2 Satellite Data

Sustainability ◽

10.3390/su13010432 ◽

2021 ◽

Vol 13 (1) ◽

pp. 432

Author(s):

Aru Han ◽

Song Qing ◽

Yongbin Bao ◽

Li Na ◽

Yuhai Bao ◽

...

Keyword(s):

Forest Fire ◽

Forest Fires ◽

Vegetation Change ◽

Fire Severity ◽

Dynamic Change ◽

Burned Area ◽

Fire Event ◽

Vegetation Dynamic ◽

Area Index ◽

Sentinel 2

An important component in improving the quality of forests is to study the interference intensity of forest fires, in order to describe the intensity of the forest fire and the vegetation recovery, and to improve the monitoring ability of the dynamic change of the forest. Using a forest fire event in Bilahe, Inner Monglia in 2017 as a case study, this study extracted the burned area based on the BAIS2 index of Sentinel-2 data for 2016–2018. The leaf area index (LAI) and fractional vegetation cover (FVC), which are more suitable for monitoring vegetation dynamic changes of a burned area, were calculated by comparing the biophysical and spectral indices. The results showed that patterns of change of LAI and FVC of various land cover types were similar post-fire. The LAI and FVC of forest and grassland were high during the pre-fire and post-fire years. During the fire year, from the fire month (May) through the next 4 months (September), the order of areas of different fire severity in terms of values of LAI and FVC was: low > moderate > high severity. During the post fire year, LAI and FVC increased rapidly in areas of different fire severity, and the ranking of areas of different fire severity in terms of values LAI and FVC was consistent with the trend observed during the pre-fire year. The results of this study can improve the understanding of the mechanisms involved in post-fire vegetation change. By using quantitative inversion, the health trajectory of the ecosystem can be rapidly determined, and therefore this method can play an irreplaceable role in the realization of sustainable development in the study area. Therefore, it is of great scientific significance to quantitatively retrieve vegetation variables by remote sensing.

Download Full-text

Empirical Research on Climate Warming Risks for Forest Fires: A Case Study of Grade I Forest Fire Danger Zone, Sichuan Province, China

Sustainability ◽

10.3390/su13147773 ◽

2021 ◽

Vol 13 (14) ◽

pp. 7773

Author(s):

San Wang ◽

Hongli Li ◽

Shukui Niu

Keyword(s):

Wind Speed ◽

Forest Fire ◽

Climate Warming ◽

Forest Fires ◽

Meteorological Factors ◽

Sichuan Province ◽

Danger Zone ◽

Climatic Regions ◽

Area Burned ◽

Forest Fire Danger

The Sichuan province is a key area for forest and grassland fire prevention in China. Forest resources contribute significantly not only to the biological gene pool in the mid latitudes but also in reducing the concentration of greenhouse gases and slowing down global warming. To study and forecast forest fire change trends in a grade I forest fire danger zone in the Sichuan province under climate change, the dynamic impacts of meteorological factors on forest fires in different climatic regions were explored and a model between them was established by using an integral regression in this study. The results showed that the dominant factor behind the area burned was wind speed in three climatic regions, particularly in Ganzi and A’ba with plateau climates. In Ganzi and A’ba, precipitation was mainly responsible for controlling the number of forest fires while it was mainly affected by temperature in Panzhihua and Liangshan with semi-humid subtropical mountain climates. Moreover, the synergistic effect of temperature, precipitation and wind speed was responsible in basin mid-subtropical humid climates with Chengdu as the center and the influence of temperature was slightly higher. The differential forest fire response to meteorological factors was observed in different climatic regions but there was some regularity. The influence of monthly precipitation in the autumn on the area burned in each climatic region was more significant than in other seasons, which verified the hypothesis of a precipitation lag effect. Climate warming and the combined impact of warming effects may lead to more frequent and severe fires.

Download Full-text

Associations Between Ambient Particulate Air Pollution and Cognitive Function in Indonesian Children Living in Forest Fire–Prone Provinces

Asia Pacific Journal of Public Health ◽

10.1177/10105395211031735 ◽

2021 ◽

pp. 101053952110317

Author(s):

Bin Jalaludin ◽

Frances L. Garden ◽

Agata Chrzanowska ◽

Budi Haryanto ◽

Christine T. Cowie ◽

...

Keyword(s):

Air Pollution ◽

Cognitive Function ◽

Forest Fire ◽

Forest Fires ◽

Regression Models ◽

Individual Factors ◽

Aerodynamic Diameter ◽

Particulate Air Pollution ◽

Multivariable Models ◽

Particulate Matter 2.5

Smoke from forest fires can reach hazardous levels for extended periods of time. We aimed to determine if there is an association between particulate matter ≤2.5 µm in aerodynamic diameter (PM2.5) and living in a forest fire–prone province and cognitive function. We used data from the Indonesian Family and Life Survey. Cognitive function was assessed by the Ravens Colored Progressive Matrices (RCPM). We used regression models to estimate associations between PM2.5 and living in a forest fire–prone province and cognitive function. In multivariable models, we found very small positive relationships between PM2.5 levels and RCPM scores (PM2.5 level at year of survey: β = 0.1%; 95% confidence interval [CI] = 0.01% to 0.19%). There were no differences in RCPM scores for children living in forest fire–prone provinces compared with children living in non-forest fire–prone provinces (mean difference = −1.16%, 95% CI = −2.53% to 0.21%). RCPM scores were lower for children who had lived in a forest fire–prone province all their lives compared with children who lived in a non-forest fire–prone province all their life (β = −1.50%; 95% CI = −2.94% to −0.07%). Living in a forest fire–prone province for a prolonged period of time negatively affected cognitive scores after adjusting for individual factors.

Download Full-text