Construction and Assessment of a Drought-Monitoring Index Based on Multi-Source Data Using a Bias-Corrected Random Forest (BCRF) Model

Agricultural drought significantly impacts agricultural production, highlighting the need for accurate monitoring. Accurate agricultural-drought-monitoring models are critical for timely warning and prevention. The random forest (RF) is a popular artificial intelligence method but has not been extensively studied for agricultural drought monitoring. Here, multi-source remote sensing data, including surface temperature, vegetation index, and soil moisture data, were used as independent variables; the 3-month standardized precipitation evapotranspiration index (SPEI_3) was used as the dependent variable. Soil texture and terrain data were used as auxiliary variables. The bias-corrected RF model was used to construct a random forest synthesized drought index (RFSDI). The drought-degree determination coefficients (R2) of the training and test sets reached 0.86 and 0.89, respectively. The RFSDI and SPEI_3 fit closely, with a correlation coefficient (R) above 0.92. The RFSDI accurately reflected typical drought years and effectively monitored agricultural drought in Northeast China (NEC). In the past 18 years, agricultural drought in NEC has generally decelerated. The degree and scope of drought impacts from 2003 to 2010 were greater than those from 2010 to 2020. Agricultural drought occurrence in NEC was associated with dominant climatic variables such as precipitation (PRE), surface temperature (Ts), relative humidity (RHU), and sunshine duration (SSD), alongside elevation and soil texture differences. The agricultural drought occurrence percentage at 50–500 m elevations reached 94.91%, and the percentage of occurrence in loam and sandy soils reached 90.31%. Water and temperature changes were significantly correlated with the occurrence of agricultural drought. Additionally, NEC showed an alternating cycle of drought and waterlogging of about 10 years. These results have significant application potential for agricultural drought monitoring and drought prevention in NEC and demonstrate a new approach to comprehensively evaluating agricultural drought.

[1]  Chong-yu Xu,et al.  Multisource data-based integrated drought monitoring index: model development and application , 2022, Journal of Hydrology.

[2]  Manzoor,et al.  Impact assessment of drought monitoring events and vegetation dynamics based on multi-satellite remote sensing data over Pakistan , 2022, Environmental Science and Pollution Research.

[3]  S. Wasti,et al.  Spatial and temporal analysis of HCHO response to drought in South Korea. , 2022, The Science of the total environment.

[4]  Chunbin Li,et al.  Spatial and temporal variations of drought in Sichuan Province from 2001 to 2020 based on modified temperature vegetation dryness index (TVDI) , 2022, Ecological Indicators.

[5]  Xiaomeng Song,et al.  An Analysis of the Impact of Groundwater Overdraft on Runoff Generation in the North China Plain with a Hydrological Modeling Framework , 2022, Water.

[6]  Hanqing Wu,et al.  Evaluating soil erosion by introducing crop residue cover and anthropogenic disturbance intensity into cropland C-factor calculation: Novel estimations from a cropland-dominant region of Northeast China , 2022, Soil and Tillage Research.

[7]  Baodong Xu,et al.  Generating High-Resolution and Long-Term SPEI Dataset over Southwest China through Downscaling EEAD Product by Machine Learning , 2022, Remote. Sens..

[8]  S. Pan,et al.  Grassland productivity response to droughts in northern China monitored by satellite-based solar-induced chlorophyll fluorescence. , 2022, The Science of the total environment.

[9]  J. Canadell,et al.  Large loss and rapid recovery of vegetation cover and aboveground biomass over forest areas in Australia during 2019–2020 , 2022, Remote Sensing of Environment.

[10]  P. Sandeep,et al.  Integrated drought monitoring index: A tool to monitor agricultural drought by using time-series datasets of space-based earth observation satellites , 2021 .

[11]  A. Islam,et al.  A comprehensive statistical assessment of drought indices to monitor drought status in Bangladesh , 2020, Arabian Journal of Geosciences.

[12]  Lei Yan,et al.  Agricultural drought monitoring using European Space Agency Sentinel 3A land surface temperature and normalized difference vegetation index imageries , 2019 .

[13]  Z. Yaseen,et al.  Copula based assessment of meteorological drought characteristics: Regional investigation of Iran , 2019, Agricultural and Forest Meteorology.

[14]  P. Guo,et al.  Drought risk evaluation model with interval number ranking and its application. , 2019, The Science of the total environment.

[15]  Ahmad Sharafati,et al.  Seasonal Drought Pattern Changes Due to Climate Variability: Case Study in Afghanistan , 2019, Water.

[16]  Guoyong Leng,et al.  Crop yield sensitivity of global major agricultural countries to droughts and the projected changes in the future , 2019, The Science of the total environment.

[17]  Vijay P. Singh,et al.  Multisource data based agricultural drought monitoring and agricultural loss in China , 2019, Global and Planetary Change.

[18]  Shuanghe Shen,et al.  Drought indices based on MODIS data compared over a maize-growing season in Songliao Plain, China , 2018, Journal of Applied Remote Sensing.

[19]  A. Bao,et al.  Space-time characterization of drought events and their impacts on vegetation in Central Asia , 2018, Journal of Hydrology.

[20]  Guoqing Zhou,et al.  DEM correction to the TVDI method on drought monitoring in karst areas , 2018, International Journal of Remote Sensing.

[21]  Wenji Zhao,et al.  Land-cover classification using GF-2 images and airborne lidar data based on Random Forest , 2018, International Journal of Remote Sensing.

[22]  Zhenghua Hu,et al.  Assessment of drought during corn growing season in Northeast China , 2018, Theoretical and Applied Climatology.

[23]  Ke Liu,et al.  Comparison of Two Simulation Methods of the Temperature Vegetation Dryness Index (TVDI) for Drought Monitoring in Semi-Arid Regions of China , 2017, Remote. Sens..

[24]  Lei Ying,et al.  Information source detection in the SIR model: A sample path based approach , 2012, 2013 Information Theory and Applications Workshop (ITA).

[25]  J. L. Sánchez,et al.  Identification of drought phases in a 110-year record from Western Mediterranean basin: Trends, anomalies and periodicity analysis for Iberian Peninsula , 2015 .

[26]  Shunlin Liang,et al.  Time‐lag effects of global vegetation responses to climate change , 2015, Global change biology.

[27]  Jongwoo Song,et al.  Bias corrections for Random Forest in regression using residual rotation , 2015 .

[28]  Li Wang,et al.  Feature Selection of Time Series MODIS Data for Early Crop Classification Using Random Forest: A Case Study in Kansas, USA , 2015, Remote. Sens..

[29]  Liang Qiao,et al.  A Review of Remote Sensing Drought Monitoring Method , 2014 .

[30]  Compton J. Tucker,et al.  Thirty-two Years of Sahelian Zone Growing Season Non-Stationary NDVI3g Patterns and Trends , 2014, Remote. Sens..

[31]  Naiming Xie,et al.  China’s regional meteorological disaster loss analysis and evaluation based on grey cluster model , 2014, Natural Hazards.

[32]  S. Vicente‐Serrano,et al.  A Multiscalar Drought Index Sensitive to Global Warming: The Standardized Precipitation Evapotranspiration Index , 2009 .

[33]  T. Tadesse,et al.  The Vegetation Drought Response Index (VegDRI): A New Integrated Approach for Monitoring Drought Stress in Vegetation , 2008 .

[34]  J. L. Parra,et al.  Very high resolution interpolated climate surfaces for global land areas , 2005 .

[35]  Jiquan Zhang,et al.  Risk assessment of drought disaster in the maize-growing region of Songliao Plain, China , 2003 .

[36]  F. Kogan,et al.  World droughts in the new millennium from AVHRR‐based vegetation health indices , 2002 .

[37]  I. Sandholt,et al.  A simple interpretation of the surface temperature/vegetation index space for assessment of surface moisture status , 2002 .