Satellite imagery and machine learning for aridity disaster classification using vegetation indices

Prasetyo, Sri Yulianto Joko; Hartomo, Kristoko Dwi; Paseleng, Mila Chrismawati; Chandra, Dian Widiyanto; Winarko, Edi

doi:10.11591/eei.v9i3.1916

Cited by 7 publications

(7 citation statements)

References 23 publications

Supporting

Mentioning

Contrasting

Unclassified

Order By: Relevance

“…In this section, some research about remote sensing based on prediction and classification are discussed. Prasetyo et al (2020) implemented spectral vegetation index to the data obtained from the Landsat 8 OLI satellite to provide disaster risk index information. k -NN with spatial autocorrelation was used to classify the drought risk areas.…”

Section: Related Workmentioning

confidence: 99%

“…In summary, it has been shown from this review that spectral vegetation indices indicated the quantitative values for measuring the vegetation canopy in receiving and reflecting the light spectrum. They were interpreted as plant’s spectral characteristics, including the infrared spectrum as visible light (IR) and the near infrared spectrum as invisible light (NIR) ( Prasetyo et al, 2020 ).…”

Section: Related Workmentioning

confidence: 99%

See 1 more Smart Citation

Vegetation indices’ spatial prediction based novel algorithm for determining tsunami risk areas and risk values

Hartomo

Nataliani

Hasibuan

2022

PeerJ Computer Science

View full text Add to dashboard Cite

This paper aims to propose a new algorithm to detect tsunami risk areas based on spatial modeling of vegetation indices and a prediction model to calculate the tsunami risk value. It employs atmospheric correction using DOS1 algorithm combined with k-NN algorithm to classify and predict tsunami-affected areas from vegetation indices data that have spatial and temporal resolutions. Meanwhile, the model uses the vegetation indices (i.e., NDWI, NDVI, SAVI), slope, and distance. The result of the experiment compared to other classification algorithms demonstrates good results for the proposed model. It has the smallest MSEs of 0.0002 for MNDWI, 0.0002 for SAVI, 0.0006 for NDVI, 0.0003 for NDWI, and 0.0003 for NDBI. The experiment also shows that the accuracy rate for the prediction model is about 93.62%.

show abstract

Section: Related Workmentioning

confidence: 99%

Section: Related Workmentioning

confidence: 99%

Vegetation indices’ spatial prediction based novel algorithm for determining tsunami risk areas and risk values

Hartomo

Nataliani

Hasibuan

2022

PeerJ Computer Science

View full text Add to dashboard Cite

show abstract

“…Random Forest merupakan metode ensemble untuk klasifikasi dan regresi penentuan wilayah gambar dan pembuatan variable dari berbagai model untuk menghitung respon berdasarkan hasil dari pohon keputusan [21] [23]. Setelah dilakukan klasifikasi dan prediksi menggunakan algoritma random forest maka dilakukan uji performa klasifikasi dengan menggunakan Cohen's Kappa yang akan menghasilkan nilai akurasi [24].…”

Section: Random Forestunclassified

Penerapan Algoritma Random Forest dalam Menganalisa Perubahan Suhu Permukaan Wilayah Kota Salatiga

Mahesti

Hartomo²,

Prasetyo³

2022

mib

View full text Add to dashboard Cite

The population increase in Salatiga city is growing rapidly from 2010 to 2020. This change affects the area with vegetation cover, increasing building density and increasing land surface temperatures. The rising of land surface temperature can affect climate change, air quality, human health quality and energy usage. The purpose of this research is to find out the effect of the area with built-up land and area with vegetation cover to land surface temperature by exploring the values of NDVI, NDBI, LST and Albedo. This research shows that the NDVI value has decreased while the NDBI, LST and Albedo values have increased from 2014 to 2021. The values of NDVI, NDBI and Albedo are the components used as validation of the value of the land surface temperature (LST) change in the study area. The results of the correlation between indices show that the highest correlation occurs between NDVI and NDBI with a value of -0.979 which has a negative correlation because vegetation density is always inversely proportional to the density of built up land. The classification results show that there are 7 villages in Salatiga City with high temperature increases, the villages name are Cebongan, Mangunsari, Ledok, Kutowinangun Kidul, Gendongan, Salatiga and Kalicacing. The results of the accuracy and kappa values in the Random Forest algorithm are quite accurate with an accuracy value of 90% and a kappa value of 73%. The usability test in this study was carried out by distributing questionnaires to city planning department in Salatiga City who had a recapitulation result of 3.62 with the criteria "quite useful". From these results, this research is in accordance with its objectives, the result can be used as one of the city government's recommendations for policy making, especially in Salatiga city planning department.

show abstract

“…The (Prasetyo, Hartomo, Paseleng, Chandra, & E. Winarko, 2020). Based on the government's policies, it is necessary to re-evaluate to find the best solution to avoid land and forest fires.…”

Section: Introductionmentioning

confidence: 99%

Identification of Land Fire Risk Areas with Random Forest Using Landsat Image Data 8 OLI

Radandima

2022

IJNSE

View full text Add to dashboard Cite

Land fire is a complex and serious problem affecting several human life sectors. Stimulating the occurrence of land fires caused by long dry seasons and erratic rainy seasons causes plants to dry up and die. Illegal land burning by irresponsible people for expansion and other interests. This study uses quantitative methods. The variables used are vegetation index values obtained from Landsat 8 OLI images. The result of this research is that data classified using the random forest algorithm at RStudio produces a default number of 500 trees, and the number of variables tested in each split is 2. So, the estimated error rate of 2 out of the bag is 0.47%. Prediction and confusion matrix - train 403 data are less risky "0" (middle risk) of a fire, and there are 22 data of high risk of "1" (high risk) of a fire, with an accuracy value of 0.9914, 1. While the second prediction of the confusion matrix - test data, there are 167 data less risky "0" (middle risk) of fire. There is 1 data with a high risk of “1” (high risk) of a fire. There are seven high-risk data "1" (high risk) of fire, with an accuracy value of 0.9943, indicating a more accurate assessment of model accuracy, and the range is still good, around 96% to 99%. There are several incorrect classifications in the prediction and confusion matrix – train, which is slightly higher than the predictions of the two-confusion matrix – test, and sensitivity: 1.0000, which is the same in both prediction and confusion matrix – train & tes.

show abstract

Satellite imagery and machine learning for aridity disaster classification using vegetation indices

Cited by 7 publications

References 23 publications

Vegetation indices’ spatial prediction based novel algorithm for determining tsunami risk areas and risk values

Vegetation indices’ spatial prediction based novel algorithm for determining tsunami risk areas and risk values

Penerapan Algoritma Random Forest dalam Menganalisa Perubahan Suhu Permukaan Wilayah Kota Salatiga

Identification of Land Fire Risk Areas with Random Forest Using Landsat Image Data 8 OLI

Contact Info

Product

Resources

About