Techno International New Town

Topic:
Analyzing green cover of an area
PRESENTED BY:
Gargi Baid – 18700120057
Gourav Agarwal – 18700120070
Mridul Singh Shyam Sukha – 18700120071
Shreyansh Jhawar – 18700120098
UNDER THE GUIDANCE OF
Prof. Nilanjana Dutta Roy
(Department of Computer Science and Engineering)
CONTENT:
• Introduction
• Problem Definition
• Methodology
• Results
• Future Scope
• Conclusion
• Bibliography
 Introduction:
The analysis of green cover in the West Bengal region employs:
• Normalized Difference Vegetation Index (NDVI) and Enhanced Vegetation Index (EVI)
techniques to assess the extent and quality of vegetation.
• This study involves studying the distribution of vegetation, and changes over time using
advanced remote sensing techniques and several air quality and land cover datasets.
• Data sources include remote sensing imagery, historical land use records, and local
environmental reports.
• The analysis offers valuable insights for urban planning, policy-making, and conservation efforts
in West Bengal, addressing challenges like data accuracy, seasonal variations, and urban
development pressures.
• Ultimate aim is to provide a comprehensive understanding of the current state of green cover
in West Bengal, offering valuable insights for urban planning, policy-making, and recommend
strategies for improvement and conservation.
Problem Definition:
• To monitor and analyze green cover over large areas in
a cost-effective and efficient manner.
• To develop effective image processing techniques to
preprocess satellite images and accurately classify land
cover into different categories.
• NDVI and EVI values to be calculated to analyze green
cover over the West Bengal region.
Methodology:
For getting the NDVI and EVI values
over the Years over the West Bengal
region, we have followed the
following Steps which is represented
in following flowchart.
 NDVI(Normalized Difference Vegetation Index)
• It is a remote sensing index that measures the health or vigor of vegetation. The
NDVI is calculated from the reflectance of two bands of electromagnetic
radiation, usually the red and near-infrared bands.
• The formula for NDVI is (NIR-RED)/(NIR+RED) Where, NIR is the reflectance in the
near-infrared band and RED is the reflectance in the red band.
• NDVI values range from -1 to +1, with negative values indicating water or other
non-vegetated surfaces, values close to zero indicating bare soil or low-
density vegetation, and values approaching +1 indicating dense and healthy
vegetation.
 EVI(Enhanced Vegetation Index)
• Enhanced Vegetation Index (EVI) is a satellite-derived index used to quantify
vegetation greenness and monitor plant growth, vegetation cover, and land cover
changes. It is similar to the Normalized Difference Vegetation Index (NDVI) but
designed to improve sensitivity in areas of high biomass and reduce atmospheric
influences.
• Formula: The formula for EVI is:
EVI=𝐺×(𝑁𝐼𝑅−𝑅𝐸𝐷)(𝑁𝐼𝑅+𝐶1×𝑅𝐸𝐷−𝐶2×𝐵𝐿𝑈𝐸+𝐿)EVI=G×(NIR+C1 ×RED−C2 ×BLUE+L)
(NIR−RED)
• EVI values range from -1 to +1, with negative values indicating water or other non-
vegetated surfaces, values close to zero indicating bare soil or low-
density vegetation, and values approaching +1 indicating dense and healthy
vegetation.
 Steps for Calculating NDVI and EVI:-
​
1. Acquire remote sensing data from satellites or aerial platforms which are available in the form of
digital images in various formats such as TIFF, JPEG, or NetCDF.​

2. Preprocess the data to remove any noise or artifacts that may affect the accuracy of the NDVI
calculation. This step may involve radiometric and atmospheric corrections, geometric corrections,
and image mosaicking.​

3. Calculate the NDVI and EVI values.

4. Interpret the NDVI and EVI results

5. Extract the red, blue and near-infrared bands as per the NDVI reflectance values from
the preprocessed remote sensing data.
​4. Calculate EVI: The EVI is calculated using the following formula: 2.5 * ((NIR – RED) / (NIR + 6 * RED –
7.5 * BLUE + 1)), where NIR is the reflectance in the near-infrared band and RED is the reflectance in the
red band and BLUE is the reflectance of blue band. The resulting EVI values range from -1 to +1, with
negative values indicating non-vegetated surfaces, and positive values indicating vegetated surfaces.
5. Interpret the NDVI and EVI results: The NDVI and EVI values can be interpreted in terms of the
following:
Negative Values (-1 to 0):
Non-vegetated Areas: Negative values usually correspond to areas without vegetation, such as water bodies,
barren and, or snow.
Zero (0):

No Vegetation: value of zero typically indicates bare soil or areas with very sparse vegetation.

Positive Values (0 to +1):

Low to Moderate Vegetation (0 to 0.3): These values indicate areas with low to moderate vegetation density, such
as grasslands, shrubs, or early stages of crop growth.
Moderate to High Vegetation (0.3 to 0.6): Higher values in this range suggest areas with denser vegetation, such as
mature crops, forests, or dense grasslands.
High Vegetation (>0.6): Values above 0.6 represent areas with very high vegetation density, such as tropical
rainforests or other dense forested areas.
Experimental Results

NDVI-EVI vs Time
NDVI values over the region for 2023
Year NDVI
2023-01-01 0.4681924500867488
2023-01-17 0.44923467675279954
2023-02-02 0.44185741505075393
2023-02-18 0.4581969327998909
2023-03-06 0.4631601354616516
2023-03-22 0.5478625589188808
2023-04-07 0.5196115549835555

Dataset Name :MOD13A1.061 Terra Vegetation Indices 16-Day Global 500m

EVI values over the region for 2023
Year EVI
2023-01-01 0.2616735241040231
2023-01-17 0.25930409496153684
2023-02-02 0.23774347011134953
2023-02-18 0.25504628357107345
2023-03-06 0.2856118002179839
2023-03-22 0.33583117059759804
2023-04-07 0.3269632089182293
2023-04-23 0.3612609445704062

Dataset Name :MOD13A1.061 Terra Vegetation Indices 16-Day Global 500m

 FUTURE SCOPE:
• Integration of satellite imagery with other data sources such as ground truth data, to improve the
accuracy of the analysis.

• Designing effective conservation strategies to identify areas of declining green cover and take
action to protect and conserve these areas.

• Predictive model: A mathematical model can be created to predict the loss rate of greenery over
time so that the respective authorities can take early actions to stop the cause.

• Using multi-spectral satellite imagery to analyze the green cover in more detail. This will involve
more than two sets of satellite images to calculate the vegetation index that can provide a more
accurate representation of green cover.
CONCLUSION:
In conclusion, comparison of green cover using
satellite imagery and image processing
techniques is a promising approach for
monitoring and managing vegetation cover in
different ecosystems. The methodology
and architecture of this approach includes
several steps such as data acquisition,
preprocessing, image enhancement, vegetation
indices, classification, accuracy assessment, and
spatial analysis.
 Bibliography
• Rouse, J. W., Haas, R. H., Schell, J. A., & Deering, D. W. (1974). Monitoring vegetation systems in the Great
Plains with ERTS. In Third Earth Resources Technology Satellite-1 Symposium-Volume I: Technical Presentations
(Vol. 1, pp. 309-317). US Government Printing Office. This seminal paper introduced the concept of NDVI for
monitoring vegetation using satellite imagery.
• Huete, A. R. (1988). A soil-adjusted vegetation index (SAVI). Remote sensing of environment, 25(3), 295-309.
This paper introduced the Enhanced Vegetation Index (EVI) method, which is an improvement over NDVI,
reducing atmospheric influences and background signals.
• Pettorelli, N., Vik, J. O., Mysterud, A., Gaillard, J. M., Tucker, C. J., & Stenseth, N. C. (2005). Using the satellite-
derived NDVI to assess ecological responses to environmental change. Trends in Ecology & Evolution, 20(9),
503-510. This paper discusses the application of NDVI in assessing ecological responses to environmental
changes.
• Jiang, Z., & Huete, A. R. (2006). MODIS vegetation index (MOD13). Algorithm theoretical basis document. This
document provides a detailed description of the algorithm used for generating MODIS NDVI and EVI products.
• Thenkabail, P. S., Lyon, J. G., & Huete, A. R. (2011). Advances in hyperspectral remote sensing of vegetation
and agricultural croplands. CRC Press. This book provides insights into the application of hyperspectral remote
sensing, including NDVI and EVI methods, in monitoring vegetation and agricultural lands.
THANK YOU!