Looking for breakthrough ideas for innovation challenges? Try Patsnap Eureka!

A multi-drought index fusion method based on structural reasoning

A technology of structural reasoning and drought index, applied in data processing applications, forecasting, instruments, etc., can solve the problem that drought index is difficult to meet the conditions that are generally applicable in space and time, and does not consider the validity of data, and achieves optimized fusion results, leakage The effect of sub-phenomenon improvement

Inactive Publication Date: 2019-01-18
嘉兴市南湖区翊轩塑料五金厂(普通合伙)
View PDF3 Cites 0 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0003] Due to the complex characteristics of drought itself and the extensive impact on society, most drought indicators are established in a specific region and time range, with corresponding time and space scales, and it is difficult for a single drought indicator to meet the universally applicable conditions in time and space
Although the current drought monitoring method has a multi-drought index fusion model based on remote sensing and meteorological observation indicators, it does not consider the validity of the data itself on the temporal and spatial scales

Method used

the structure of the environmentally friendly knitted fabric provided by the present invention; figure 2 Flow chart of the yarn wrapping machine for environmentally friendly knitted fabrics and storage devices; image 3 Is the parameter map of the yarn covering machine
View more

Image

Smart Image Click on the blue labels to locate them in the text.
Viewing Examples
Smart Image
  • A multi-drought index fusion method based on structural reasoning
  • A multi-drought index fusion method based on structural reasoning
  • A multi-drought index fusion method based on structural reasoning

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0025] Below in conjunction with accompanying drawing and embodiment example, the present invention will be further described:

[0026] A multi-drought index fusion method based on structural reasoning, including:

[0027] First define each symbol:

[0028] latent state {l 0 ... l N-1}, model variable (model variable) (also can be regarded as a recessive state) m 1 and m 2 ;

[0029] sequence of observations (t=1,...,T), wherein, T is the dimension of time series;

[0030] Initial state, mode probability distribution P(l t=1 (i)), and abbreviated as and

[0031] Recessive state transition probability P(l t (i)|l t-1 (i′)), (i, i′=1,...,N), abbreviated as or implicit state transition matrix P(l t |l t-1 ), abbreviated as a l ;

[0032] mode transition probability and (j, j', k, k'=0, 1), respectively abbreviated as and or mode transition matrix and Respectively abbreviated as a m1 and a m2 ;

[0033] Observation Probability abbreviated as b...

the structure of the environmentally friendly knitted fabric provided by the present invention; figure 2 Flow chart of the yarn wrapping machine for environmentally friendly knitted fabrics and storage devices; image 3 Is the parameter map of the yarn covering machine
Login to View More

PUM

No PUM Login to View More

Abstract

The invention relates to a multi-drought index fusion method based on structure inference, which comprises the steps of carrying out structure reasoning, determining two characteristic model variables m1, m2 of a target 1, carrying out mode selection according to a relation between the two characteristic model variables m1, m2, and estimating the joint probability in the mode; and carrying out time dimension extension on structure inference, adopting an FHMM (Factorial Hidden Markov Model), acquiring model parameters of the FHMM, bringing the model parameters into the FHMM, and estimating fusion of multiple drought indexes at the current time point. According to the invention, the effectiveness of each index in the time dimension is considered, a fusion effect is optimized, phenomena of misclassification and missed classification of an SPI and a PV-VCI are improved to a certain degree, monitored drought is concentrated in spatial layout, and the goodness of fit with DM monitoring is good. Therefore, the multi-drought index fusion method can provide an auxiliary means for crop drought monitoring.

Description

technical field [0001] The invention relates to a multi-drought index fusion method based on structural reasoning. Background technique [0002] With the intensification of global climate change, the temperature continues to rise, the frequency and intensity of drought continue to increase, the expansion of arid areas and the degree of aridity are becoming more and more serious, and the trend of aridification has become the focus of global attention. In the case of no or little rain for a long time, the soil moisture is deficient, and evapotranspiration makes the water balance in the crops seriously imbalanced, and the normal physiological activities are destroyed, thus triggering crop drought events. China is in a monsoon climate zone, and the rainfall is unevenly distributed, which makes the drought problem particularly prominent. The area of ​​China's perennial crops is about 2×10 7 ~2.7×10 7 hm 2 , resulting in an annual food loss of about 2.5×10 10 ~3×10 10 kg, acc...

Claims

the structure of the environmentally friendly knitted fabric provided by the present invention; figure 2 Flow chart of the yarn wrapping machine for environmentally friendly knitted fabrics and storage devices; image 3 Is the parameter map of the yarn covering machine
Login to View More

Application Information

Patent Timeline
no application Login to View More
Patent Type & Authority Patents(China)
IPC IPC(8): G06Q10/04G06Q50/02
Inventor 沈永林
Owner 嘉兴市南湖区翊轩塑料五金厂(普通合伙)
Who we serve
  • R&D Engineer
  • R&D Manager
  • IP Professional
Why Patsnap Eureka
  • Industry Leading Data Capabilities
  • Powerful AI technology
  • Patent DNA Extraction
Social media
Patsnap Eureka Blog
Learn More
PatSnap group products