Correlating night-time satellite images with poverty and other census data of India and estimating future trends

Nischal, K. N.; Radhakrishnan, Radhika; Mehta, Sanket; Chandani, Sumit

doi:10.1145/2732587.2732597

Cited by 7 publications

(5 citation statements)

References 0 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Using classification maps created by ML categorization algorithms on a specific geographic area around Nirma University, Ahmadabad, India, this research provides a unique way for change detection analysis. [11] Luo, H., et al [2017] Forest fire area can't be accurately predicted using the Multivariate Linear Regression Model due to an error in interpreting the linear connection between independent and dependent variables. Data are modelled, and a fire's likely path is predicted using an approach called ridge regression.…”

Section: Literature Surveymentioning

confidence: 99%

Prediction of Housing Price and Forest Cover Using Mosaics with Uncertain Satellite Imagery

Sai

Rao

Vani

et al. 2022

IJRITCC

View full text Add to dashboard Cite

The growing world is more expensive to estimate land use, road length, and forest cover using a plant-scaled ground monitoring system. Satellite imaging contains a significant amount of detailed uncertain information. Combining this with machine learning aids in the organization of these data and the estimation of each variable separately. The resources necessary to deploy Machine learning technologies for Remote sensing images, on the other hand, restrict their reach ability and application. Based on satellite observations which are notably underutilised in impoverished nations, while practical competence to implement SIML might be restricted. Encoded forms of images are shared across tasks, and they will be calculated and sent to an infinite number of researchers who can achieve top-tier SIML performance by training a regression analysis onto the actual data. By separating the duties, the proposed SIML solution, MOSAIKS, shapes SIML approachable and global. A Featurization stage turns remote sensing data into concise vector representations, and a regression step makes it possible to learn the correlations which are specific to its particular task which link the obtained characteristics to the set of uncertain data.

show abstract

Section: Literature Surveymentioning

confidence: 99%

Prediction of Housing Price and Forest Cover Using Mosaics with Uncertain Satellite Imagery

Sai

Rao

Vani

et al. 2022

IJRITCC

View full text Add to dashboard Cite

show abstract

“…Where is the intensity for pixel , is total pixels in the sub-district region, ( ) is the light intensity for sub-district (Nischal et al, 2015).…”

Section: Night-time Light Intensity Extraction and Validationmentioning

confidence: 99%

“…Thirdly, we imputed the 60 missing household income data using the four different datasets from Section 3.1.2. The imputation results from each difference set of variables were illustrated in Figure 8 (4), (5), (6), and (7).…”

Section: Income Imputation Model Implementationmentioning

confidence: 99%

SOCIOECONOMIC STATUS FROM SPACE: EXAMPLE OF ESTIMATING THAILAND’s SUB-DISTRICT HOUSEHOLD INCOME BASED ON REMOTELY SENSED AND GEOSPATIAL DATA

Hutasavi

Chen

2020

Int. Arch. Photogramm. Remote Sens. Spatial Inf. Sci.

View full text Add to dashboard Cite

Abstract. The socioeconomic data, such as household income, is an important indicator of people’s well-being. However, due to the limited resource in many developing countries such as Thailand, the data obtained from household income surveys are often incomplete. As a result, the annual household survey usually contains a gap at the municipality household level. In this study, we aim to quantify the household income with K-NN imputation models at the sub-district level using satellite imageries and geospatial data as proxies to socioeconomic indicators. We examined the role of satellite and geospatial data in household income estimation, applied the K-NN imputation methods to estimate the missing income data by using various geographical and statistical variables, and quantified how these data improved the accuracy of sub-district household income estimation. Our results illustrated a significant correlation between sub-district household income and geographical data extracted from day-night satellite data, such as night light intensity (r = 0.53), urban density (r = 0.44), residential area (r = 0.68), urban area (r = 0.64), and statistical data as well as household expenditure (r = 0.97). These can be used to improve the socioeconomic indicators’ estimation as well as household income in sub-district level. The income imputation from geographical data perform better result than purely statistical variables. Especially, the night light intensity can infer the wealth of people living in large scale areas, while day-time satellite images can be interpreted for land use and land cover also implying socioeconomic status. Such socioeconomic proxy from space provides spatially explicit information in further study.

show abstract

“…In contrast, our approach does not require any manual annotation of images. Nischal et al (Nischal et al 2015) correlate nighttime light intensity calculated from a single image of India with census data at the state level only. On the other hand, we estimate statistics at a significantly finer level of villages and sub-districts 1 .…”

Section: Related Workmentioning

confidence: 99%

Multi-Task Deep Learning for Predicting Poverty From Satellite Images

Pandey¹,

Agarwal²,

Krishnan

2018

AAAI

View full text Add to dashboard Cite

Estimating economic and developmental parameters such as poverty levels of a region from satellite imagery is a challenging problem that has many applications. We propose a two step approach to predict poverty in a rural region from satellite imagery. First, we engineer a multi-task fully convolutional deep network for simultaneously predicting the material of roof, source of lighting and source of drinking water from satellite images. Second, we use the predicted developmental statistics to estimate poverty. Using full-size satellite imagery as input, and without pre-trained weights, our models are able to learn meaningful features including roads, water bodies and farm lands, and achieve a performance that is close to the optimum. In addition to speeding up the training process, the multi-task fully convolutional model is able to discern task specific and independent feature representations.

show abstract

Correlating night-time satellite images with poverty and other census data of India and estimating future trends

Cited by 7 publications

References 0 publications

Prediction of Housing Price and Forest Cover Using Mosaics with Uncertain Satellite Imagery

Prediction of Housing Price and Forest Cover Using Mosaics with Uncertain Satellite Imagery

SOCIOECONOMIC STATUS FROM SPACE: EXAMPLE OF ESTIMATING THAILAND’s SUB-DISTRICT HOUSEHOLD INCOME BASED ON REMOTELY SENSED AND GEOSPATIAL DATA

Multi-Task Deep Learning for Predicting Poverty From Satellite Images

Contact Info

Product

Resources

About