A machine learning model for drought tracking and forecasting using remote precipitation data and a standardized precipitation index from arid regions

Bouaziz, Moncef; Medhioub, Emna; Csaplovisc, Elmar

doi:10.1016/j.jaridenv.2021.104478

Cited by 34 publications

(14 citation statements)

References 33 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…CHIRPS is available daily and at a spatial resolution of about 5 km. The CHIRPS precipitation data are highly reliable to identify wet and dry periods in our study region [62].…”

Section: Upimentioning

confidence: 85%

Analysis of Multispectral Drought Indices in Central Tunisia

et al. 2022

View full text Add to dashboard Cite

Surface water stress remote sensing indices can be very helpful to monitor the impact of drought on agro-ecosystems, and serve as early warning indicators to avoid further damages to the crop productivity. In this study, we compare indices from three different spectral domains: the plant water use derived from evapotranspiration retrieved using data from the thermal infrared domain, the root zone soil moisture at low resolution derived from the microwave domain using the Soil Water Index (SWI), and the active vegetation fraction cover deduced from the Normalized Difference Vegetation Index (NDVI) time series. The thermal stress index is computed from a dual-source model Soil Plant Atmosphere and Remote Evapotranspiration (SPARSE) that relies on meteorological variables and remote sensing data. In order to extend in time the available meteorological series, we compare the use of a statistical downscaling method applied to reanalysis data with the use of the unprocessed reanalysis data. Our study shows that thermal indices show comparable performance overall compared to the SWI at better resolution. However, thermal indices are more sensitive for a drought period and tend to react quickly to water stress.

show abstract

“…CHIRPS is available daily and at a spatial resolution of about 5 km. The CHIRPS precipitation data are highly reliable to identify wet and dry periods in our study region [62].…”

Section: Upimentioning

confidence: 85%

Analysis of Multispectral Drought Indices in Central Tunisia

et al. 2022

View full text Add to dashboard Cite

show abstract

“…The length of the data records is required to be at least 30 years. In order to obtain the cumulative probability, this method fits the precipitation data series into a gamma probability density function, and then normalizes it to obtain the SPI value (Tirivarombo et al, 2018;Bouaziz et al, 2021). The SPI value can be calculated as follows:…”

Section: Standardized Precipitation Indexmentioning

confidence: 99%

Comparative study on appropriate drought and flood index selection in a tropical farming island in China

Zou

Zhu²,

He³

et al. 2023

Front. Earth Sci.

View full text Add to dashboard Cite

The traditional drought and flood analysis method had not fully considered the proportion analysis of different drought and flood grades in the historical years of each rainfall station. This made results unconvincing and made it difficult to deeply understand the characteristics and applicability of various methods. Based on the daily rainfall data of 88 stations in Hainan Island from 1970 to 2019, the China-Z index and the Standardized Precipitation Index (SPI) were used to compare and analyze the spatial and temporal distribution characteristics of droughts and floods from three different time scales (flood season, non-flood season and the whole year). The results showed that both SPI and China-Z index can well reflect the actual drought and flood situations in Hainan Island. The analysis of the proportions of different drought and flood grades in the historical years of each rainfall station and regional historical drought and flood statistics suggested that the China-Z index had a better indication effect than SPI on the extreme drought and flood grades. The alternation of drought and flood between different eras were obvious. Hainan Island generally presented an east-west reverse drought-flood variation trend, as well as a north-south reverse drought-flood variation trend. The drought and flood in the central mountainous area of Hainan Island had been relatively stable. The distribution pattern of drought and flood had a good spatial consistency in the three periods. On the whole, Hainan Island had shown a trend of flood in the east and drought in the west in the past 50 years.

show abstract

“…According to the existing related research (Bouaziz et al 2021) and the research on SPI index in Yulin area (Kong et al 2021), the SPI drought classification standard is shown in Table 1.…”

Section: Process Description Of Drought Eventsmentioning

confidence: 99%

The dynamic identification mechanism research of drought based on process description

Xie

Yang

et al. 2022

Water Supply

View full text Add to dashboard Cite

Drought is one of the most common natural disasters, which can cause heavy losses on a global scale. Strengthening the research on drought identification mechanism has an important guiding role in drought disaster prevention and mitigation. The current drought identification is mostly static in the process of drought, and there is a problem that the historical evaluation information and the drought prediction information are not closely combined, with limited application value. Based on the physical cumulative and recessional effects of drought events, this paper further uses the Standardized Precipitation Index (SPI) to divide the whole drought process into four stages: accumulation → outbreak → reaction → restoration. In addition, this study proposes a new dynamic identification mechanism based on drought process, and develops a drought prediction model combining singular spectrum analysis and BP neural network (SSA-BPNN), filling the gap between scientific research and practical application. Using three drought events in the Yulin region of China as examples for simulation studies, the results show that the use of the new mechanism can not only improve the application value of the SSA-BPNN model, but also effectively advance the drought preparation time and resistance level.

show abstract

A machine learning model for drought tracking and forecasting using remote precipitation data and a standardized precipitation index from arid regions

Cited by 34 publications

References 33 publications

Analysis of Multispectral Drought Indices in Central Tunisia

Analysis of Multispectral Drought Indices in Central Tunisia

Comparative study on appropriate drought and flood index selection in a tropical farming island in China

The dynamic identification mechanism research of drought based on process description

Contact Info

Product

Resources

About