Satellite imagery and machine learning for identification of aridity risk in central Java Indonesia

This study aims to develop a software framework for predicting aridity using vegetation indices (VI) from LANDSAT 8 OLI images. VI data are predicted using machine learning (ml): Random Forest (RF) and Correlation and Regression Trees (CART). Comparison of prediction using Artificial Neural Network (ANN), Support Vector Machine (SVM), k-nearest neighbors (k-nn) and Multivariate Adaptive Regression Spline (MARS). Prediction results are interpolated using Inverse Distance Weight (IDW). This study was conducted in stages: (1) Image preprocessing; (2) calculating numerical data extracted from the LANDSAT band imagery using vegetation indices; (3) analyzing correlation coefficients between VI; (4) prediction using RF and CART; (5) comparing performances between RF and CART using ANN, SVM, k-nn, and MARS; (6) testing the accuracy of prediction using Mean Square Error (MSE) and Mean Absolute Percentage Error (MAPE); (7) interpolating with IDW. Correlation coefficient of VI data shows a positive correlation, the lowest r (0.07) and the highest r (0.98). The experiments show that the RF and CART algorithms have efficiency and effectivity in determining the aridity areas better than the ANN, SVM, k-nn, and MARS algorithm. RF has a difference between the predicted results and 1.04% survey data MAPE and the smallest value close to zero is 0.05 MSE. CART has a difference between the predicted results and 1.05% survey data MAPE and the smallest value approaching to zero which is 0.05 MSE. The prediction results of VI show that in 2020 most of the study areas were low vegetation areas with the Normalized Difference Vegetation Index (NDVI) < 0.21, had an indication of drought with the Vegetation Health Index (VHI) < 31.10, had a Vegetation Condition Index (VCI) in some areas between 35%–50% (moderate drought) and < 35% (high drought). The Burn Area Index (dBAI) values are between −3, 971 and −2,376 that show the areas have a low fire risk, and index values are between −0, 208 and −0,412 that show the areas are starting vegetation growth. The result of this study shows that the machine learning algorithms is an accurate and stable algorithm in predicting the risks of drought and land fire based on the VI data extracted from the LANDSAT 8 OLL imagery. The VI data contain the record of vegetation condition and its environment, including humidity, temperatures, and the environmental vegetation health.

[1]  Maycol Alejandro Zaraza Aguilera Classication Of Land-Cover Through Machine Learning Algorithms For Fusion Of Sentinel-2a And Planetscope Imagery , 2020, 2020 IEEE Latin American GRSS & ISPRS Remote Sensing Conference (LAGIRS).

[2]  Tian Han,et al.  Characterizing boreal forest wildfire with multi-temporal Landsat and LIDAR data , 2009 .

[3]  C. Maftei,et al.  Assessment of Multi-spectral Vegetation Indices using Remote Sensing and Grid Computing , 2011 .

[4]  Agricultural drought characteristics identification and analysis of Henan Province in China , 2014 .

[5]  Bogdan Zagajewski,et al.  Comparison of support vector machine, random forest and neural network classifiers for tree species classification on airborne hyperspectral APEX images , 2017 .

[6]  D. Bui,et al.  Satellite-Based, Multi-Indices for Evaluation of Agricultural Droughts in a Highly Dynamic Tropical Catchment, Central Vietnam , 2018 .

[7]  E. Chuvieco,et al.  Global burned-land estimation in Latin America using MODIS composite data. , 2008, Ecological applications : a publication of the Ecological Society of America.

[8]  Huawei Wan,et al.  Estimating the area burned by agricultural fires from Landsat 8 Data using the Vegetation Difference Index and Burn Scar Index , 2018 .

[9]  Hui Yang,et al.  Machine learning and artificial intelligence to aid climate change research and preparedness , 2019, Environmental Research Letters.

[10]  Jan Adamowski,et al.  Drought forecasting using new machine learning methods / Prognozowanie suszy z wykorzystaniem automatycznych samouczących się metod , 2013 .

[11]  Nguyen Doan Phuoc,et al.  Temperature prediction and model predictive control (MPC) of a distillation column using an artificial neural network based model , 2017, 2017 International Conference on System Science and Engineering (ICSSE).

[12]  C. Bourque,et al.  Evaluation of the suitability of six drought indices in naturally growing, transitional vegetation zones in Inner Mongolia (China) , 2020, PloS one.

[13]  Dar A. Roberts,et al.  Exploring the correlation between Southern Africa NDVI and Pacific sea surface temperatures: Results for the 1998 maize growing season , 1999 .

[14]  Jun Zhao,et al.  The Classification Performance and Mechanism of Machine Learning Algorithms in Winter Wheat Mapping Using Sentinel-2 10 m Resolution Imagery , 2020, Applied Sciences.

[15]  Christos Faloutsos,et al.  Storage device performance prediction with CART models , 2004, The IEEE Computer Society's 12th Annual International Symposium on Modeling, Analysis, and Simulation of Computer and Telecommunications Systems, 2004. (MASCOTS 2004). Proceedings..

[16]  Jiahua Zhang,et al.  Evaluation of Temperature Vegetation Dryness Index on Drought Monitoring Over Eurasia , 2020, IEEE Access.

[17]  A. Karakacan Kuzucu,et al.  TESTING THE POTENTIAL OF VEGETATION INDICES FOR LAND USE/COVER CLASSIFICATION USING HIGH RESOLUTION DATA , 2017 .

[18]  Vinay Kumar Sehgal,et al.  DEVELOPING VEGETATION HEALTH INDEX FROM BIOPHYSICAL VARIABLES DERIVEDUSING MODIS SATELLITE DATA IN THE TRANS-GANGETIC PLAINS OF INDIA , 2013 .

[19]  Fan Yang,et al.  Estimating grassland LAI using the Random Forests approach and Landsat imagery in the meadow steppe of Hulunber, China , 2017 .

[20]  Ying Li,et al.  K-Nearest Neighbor combined with guided filter for hyperspectral image classification , 2017, IIKI.

[21]  D. Dutta,et al.  Assessment of agricultural drought in Rajasthan (India) using remote sensing derived Vegetation Condition Index (VCI) and Standardized Precipitation Index (SPI) , 2015 .

[22]  Miguel Angel Uribe-Opazo,et al.  Spatial autocorrelation of ndvi and gvi indices derived from landsat/tm images for soybean crops in the western of the state of Paraná in 2004/2005 crop season , 2013 .

[23]  H. Hashim,et al.  URBAN VEGETATION CLASSIFICATION WITH NDVI THRESHOLD VALUE METHOD WITH VERY HIGH RESOLUTION (VHR) PLEIADES IMAGERY , 2019, The International Archives of the Photogrammetry, Remote Sensing and Spatial Information Sciences.

[24]  M. Paseleng,et al.  Computer Assisted Learning on Aridity Disaster Learning Using SIMIA (Satellite Imagery for Modelling Index of Aridity) , 2019, Journal of Physics: Conference Series.

[25]  Jayawardhana Wgnn,et al.  Investigate the Sensitivity of the Satellite-Based Agricultural Drought Indices to Monitor the Drought Condition of Paddy and Introduction to Enhanced Multi-Temporal Drought Indices , 2020 .

[26]  Sergio M. Vicente-Serrano,et al.  Drought impacts on vegetation activity in the Mediterranean region: An assessment using remote sensing data and multi-scale drought indicators , 2017 .

[27]  O. Dikinya,et al.  Using Drought Indices to Model the Statistical Relationships Between Meteorological and Agricultural Drought in Raya and Its Environs, Northern Ethiopia , 2018, Earth Systems and Environment.

[28]  D. Godone,et al.  COMPARISONS BETWEEN DIFFERENT INTERPOLATION TECHNIQUES , 2014 .

[29]  Tsegaye Tadesse,et al.  Evaluation of Satellite-Based Rainfall Estimates and Application to Monitor Meteorological Drought for the Upper Blue Nile Basin, Ethiopia , 2017, Remote. Sens..

[30]  Yakov A. Pachepsky,et al.  Developing the vegetation drought response index for South Korea (VegDRI-SKorea) to assess the vegetation condition during drought events , 2018 .

[31]  Christos Faloutsos,et al.  Storage device performance prediction with CART models , 2004, The IEEE Computer Society's 12th Annual International Symposium on Modeling, Analysis, and Simulation of Computer and Telecommunications Systems, 2004. (MASCOTS 2004). Proceedings..

[32]  Carol Miller,et al.  A New Metric for Quantifying Burn Severity: The Relativized Burn Ratio , 2014, Remote. Sens..

[33]  Wanchang Zhang,et al.  Monitoring and Assessment of Drought Focused on Its Impact on Sorghum Yield over Sudan by Using Meteorological Drought Indices for the Period 2001-2011 , 2018, Remote. Sens..

[34]  László Makra,et al.  The Palmer Drought Severity Index (PDSI) as an indicator of soil moisture , 2005 .

[35]  ICOLAS,et al.  Global burned-land estimation in Latin America using MODIS composite data , 2017 .

[36]  Amir Hossein Alavi,et al.  Machine learning in geosciences and remote sensing , 2016 .

[37]  Timothy A. Warner,et al.  Implementation of machine-learning classification in remote sensing: an applied review , 2018 .

[38]  Xiaoxia Wang,et al.  Comparison of Four Machine Learning Methods for Generating the GLASS Fractional Vegetation Cover Product from MODIS Data , 2016, Remote. Sens..