AU2021100002A4 - Technique to gis modelling of water bodies by mapping riparian vegetation along the shore - Google Patents

Technique to gis modelling of water bodies by mapping riparian vegetation along the shore Download PDF

Info

Publication number
AU2021100002A4
AU2021100002A4 AU2021100002A AU2021100002A AU2021100002A4 AU 2021100002 A4 AU2021100002 A4 AU 2021100002A4 AU 2021100002 A AU2021100002 A AU 2021100002A AU 2021100002 A AU2021100002 A AU 2021100002A AU 2021100002 A4 AU2021100002 A4 AU 2021100002A4
Authority
AU
Australia
Prior art keywords
gis
water bodies
shore
ecosystem
mapping
Prior art date
Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
Ceased
Application number
AU2021100002A
Inventor
Prathik A
Prasun Chakrabarti
Tulika Chakrabarti
Reddappa H.N
S. Mahendran
Deepa Nair
Sitanshu Sekhar Patra
Kalyani Pradhan
Ajay Kumar Prusty
Sandeep Rout
R. Sabitha
K Uma
Current Assignee (The listed assignees may be inaccurate. Google has not performed a legal analysis and makes no representation or warranty as to the accuracy of the list.)
A Prathik Dr
Nair Deepa Prof
Pradhan Kalyani Dr
Sabitha R Dr
Uma K Dr
Original Assignee
A Prathik Dr
H N Reddappa Dr
Nair Deepa Prof
Pradhan Kalyani Dr
Sabitha R Dr
Uma K Dr
Priority date (The priority date is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the date listed.)
Filing date
Publication date
Application filed by A Prathik Dr, H N Reddappa Dr, Nair Deepa Prof, Pradhan Kalyani Dr, Sabitha R Dr, Uma K Dr filed Critical A Prathik Dr
Priority to AU2021100002A priority Critical patent/AU2021100002A4/en
Application granted granted Critical
Publication of AU2021100002A4 publication Critical patent/AU2021100002A4/en
Ceased legal-status Critical Current
Anticipated expiration legal-status Critical

Links

Classifications

    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
    • G06T17/00—Three dimensional [3D] modelling, e.g. data description of 3D objects
    • G06T17/05—Geographic models
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
    • G06T7/00—Image analysis
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
    • G06V10/00—Arrangements for image or video recognition or understanding
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
    • G06V20/00—Scenes; Scene-specific elements
    • G06V20/10—Terrestrial scenes
    • G06V20/188—Vegetation
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
    • G06N20/00—Machine learning
    • G06N20/20—Ensemble learning
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
    • G06T2207/00—Indexing scheme for image analysis or image enhancement
    • G06T2207/10—Image acquisition modality
    • G06T2207/10032—Satellite or aerial image; Remote sensing
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
    • G06T2207/00—Indexing scheme for image analysis or image enhancement
    • G06T2207/30—Subject of image; Context of image processing
    • G06T2207/30181—Earth observation

Landscapes

  • Engineering & Computer Science (AREA)
  • Physics & Mathematics (AREA)
  • General Physics & Mathematics (AREA)
  • Theoretical Computer Science (AREA)
  • Multimedia (AREA)
  • Software Systems (AREA)
  • Geometry (AREA)
  • Computer Graphics (AREA)
  • Remote Sensing (AREA)
  • Computer Vision & Pattern Recognition (AREA)
  • Health & Medical Sciences (AREA)
  • General Health & Medical Sciences (AREA)
  • Image Processing (AREA)

Abstract

TECHNIQUE TO GIS MODELLING OF WATER BODIES BY MAPPING RIPARIAN VEGETATION ALONG THE SHORE ABSTRACT As the riverine ecosystem provides life support services in and around natural watercourse like river or lake, the riparian vegetation must be taken for the study using GIS modeling to determine the ecosystem services across the shore. As the riparian vegetation is an interface between the water bodies and the land cover, identification of land cover must be done as it involves erosion prevention, purification of water, plant habitats, and its surroundings. The image data of land satellites are collected using sensors, smart cameras, and smart devices. It has to be resampled for its simplicity using the Nearest Neighbour algorithm as preprocessing of the image. The collected, resampled data are to be generated as subsets. The huge data of the satellite image that has been created as subsets are stored in a cloud platform through the gateway interface. Then the Leo Breiman RF classifier in ML algorithm is deployed to classify the image data and can be visualized in smart devices. From the GIS modeled data, ecosystem valuation and the services can be further determined. 1 TECHNIQUE TO GIS MODELLING OF WATER BODIES BY MAPPING RIPARIAN VEGETATION ALONG THE SHORE Drawings DATA COLLECTION - LAND SATELLITE IMAGE IMAGE PREPROCESSING GENERATION OF SUBSETS GATEWAY CLOUD MACHINE LEARNING SUPERVISED METHOD LEO BREIMAN RANDOM FOREST CLASSIFIER VISUALIZATION OF RESULTS Fig. 1. PROCESS FLOW DIAGRAM 1

Description

TECHNIQUE TO GIS MODELLING OF WATER BODIES BY MAPPING RIPARIAN VEGETATION ALONG THE SHORE
Drawings
DATA COLLECTION - LAND SATELLITE IMAGE IMAGE PREPROCESSING GENERATION OF SUBSETS GATEWAY CLOUD MACHINE LEARNING SUPERVISED METHOD LEO BREIMAN RANDOM FOREST CLASSIFIER VISUALIZATION OF RESULTS
Fig. 1. PROCESS FLOW DIAGRAM
TECHNIQUE TO GIS MODELLING OF WATER BODIES BY MAPPING RIPARIAN VEGETATION ALONG THE SHORE DESCRIPTION
Field of the Invention.
The Field of the invention is related to machine learning algorithm Leo Breiman Random forest classifier in GIS modeling of water bodies by mapping riparian vegetation along the shore.
Background of the invention.
The ecosystem vegetation and its services have a great impact on the geographical land cover of the land. Especially, the living depends on natural resources from ecosystems for minerals, pharmaceutical, shelter, food, etc. Simultaneously, the ecosystem also provides life support services like purification of water, prevention of soil erosion, prevention of pollution of the environment, etc.
The ecosystem services and its maintenance depend completely on the human being. Determination of the status of the ecosystem and the analysis by human intervention is time-consuming and costly. The threats for the ecosystem must be identified at right time and necessary precautions must be taken. If not properly determined, it may lead to negative effects on the ecosystem.
In maintaining the ecosystem for the living, the riparian vegetation plays a vital role as it has many societal benefits like habitat and food for wildlife and water bodies. Most importantly, the riparian area serves as an interface between the river and the land i.e., upland ecosystem and the water bodies. There is a need to provide land cover geographical information for deploying environment policies implementation.
Several relationships exist between the riverine ecosystem and the riparian vegetation, that provides services to the vegetation to the river and the surrounding communities. To understand and protect the ecosystem, there is a need to study the ecosystem. So, it requires a geographical information system (GIS) modeling to be deployed for the study of the ecosystem.
Initially, images of different maps of the location are captured using sensors, smart cameras, and devices. The information or the data are collected are the satellite images of the land for GIS modeling to train the data. Riparian vegetation of various types on the banks of the river or any natural watercourse is captured. There are different classes like a forest, pasture, urban fabric, and arable land known as CORINE, coordination of information in the environment. The land cover database collected combined with information like the climate of that location, soil types in that area, etc.
The image that is captured consists of primary composite colors namely red, blue, and green. The image that is collected is to be preprocessed. If required, resampling can be done by the Nearest Neighbour algorithm for clustering the image data.
After clustering, subsets are generated and stored in the cloud through the gateway interface. The cloud platform is deployed to store a huge volume of information or data.
To communicate land use, along with information system integration, classification of Riparian vegetation deployed to interpret and monitor management. It also captures the diversity and variability of riparian vegetation. The classification of the satellite image is performed by machine learning supervised method, Leo Breiman Random Forest classifier. It obtains reliable and high-speed classifier processing. It also produces accurate results and can be visualized by smart devices.
This GIS modeling technique of the water bodies by mapping riparian vegetation along the shore not only classify the land cover but also helps to identify the ecosystem services and the relationship between the riparian vegetation and the river ecosystem by economic value calculation of the riparian vegetation along with the water bodies and indication of the state of the ecosystem by macroinvertebrates.
Objects of the Invention
The first objective is to collect the satellite image of the landscape using sensors, smart cameras, and devices. The second objective is to perform image preprocessing, creating subsets, and store the information in a cloud via a gateway. The third objective is to deploy supervised learning, Leo Breiman Random Forest classifier in the machine learning algorithm.
The riparian vegetation must be taken for study using GIS modeling to determine the ecosystem services across the shore as it is an interface between the water bodies and the land cover. The land cover must be identified as it involves erosion prevention, purification of water, plant habitats, and its surroundings. The image data of land satellites are collected using sensors, smart cameras, and smart devices. It must be resampled for its simplicity using the Nearest Neighbour algorithm as preprocessing of the image. The collected, resampled data are to be generated as subsets. The huge data of the satellite image that has been created as subsets are stored in a cloud platform through the gateway interface. Then the Leo Breiman RF classifier in ML algorithm is deployed to classify the image data and can be visualized in smart devices. From the GIS modeled data, ecosystem valuation and the services can be further determined.
Summary of the Invention
The classification of land cover is especially important as the riparian vegetation interface the land cover and the riverine vegetation i.e., upland ecosystem and the water bodies. There is a need to provide land cover geographical information for deploying environment policies implementation as it determines the ecosystem services for preserving natural resources. The images of different types of riparian vegetation must be taken for the study using GIS modeling to determine the ecosystem services across the shore as it is an interface between the water bodies and the land cover. The land cover must be identified as it involves erosion prevention, purification of water, plant habitats, and its surroundings. The image data of land satellites are collected using sensors, smart cameras, and smart devices. It has to be resampled for its simplicity using the Nearest Neighbour algorithm as preprocessing of the image. The collected, resampled data are to be generated as subsets. The huge data of the satellite image that has been created as subsets are stored in a cloud platform through the gateway interface. Then the Leo Breiman RF classifier in ML algorithm is deployed to classify the image data and can be visualized in smart devices. From the GIS modeled data, ecosystem valuation and the services can be further determined.
Detailed Description of the Invention
Fig. 1 illustrates the process flow diagram of GIS modeling of water bodies by mapping riparian vegetation along the shore.
Fig. 2 illustrates the identification process relating ecosystem system and riparian vegetation.
Detailed Description of the Invention
Fig. 1 illustrates the process flow diagram of GIS modeling of water bodies by mapping riparian vegetation along the shore. As the riverine ecosystem provides life support services like purification of water, prevention of soil erosion, prevention of pollution of the environment, etc., the classification of land cover becomes especially important. The riparian vegetation interfaces the land cover and the riverine vegetation i.e., upland ecosystem and the water bodies. There is also a need to provide geographical information on the land cover for deploying environment policies implementation as it determines the ecosystem services for preserving natural resources. Different riparian vegetation must be taken for the study using GIS modeling to determine the ecosystem services across the shore as it is an interface between the water bodies and the land cover. The image data of land satellites are collected using sensors, smart cameras, and smart devices. The image data that are collected are satellite images of the land with primary composite colors red, green, and blue for the GIS modeling to train the data. Riparian vegetation of various types on the riverbanks or any natural watercourse is captured. Database of different classes like a forest, pasture, urban fabric, and arable land are collected combined with information like the climate of that location, soil types in that area, etc. It must be resampled for its simplicity using the Nearest Neighbour algorithm as preprocessing of the image i.e clustering. The collected resampled data are to be generated as subsets. The huge data of the satellite image that has been created as subsets are stored in a cloud platform through the gateway interface. To communicate, interpret, and monitor management, the classification of Riparian vegetation is deployed. It also captures the diversity and variability of riparian vegetation. The Leo Breiman RF classifier in the ML algorithm is deployed to classify the image data and can be visualized in smart devices. From the GIS modeled data, ecosystem valuation and the services can be further determined.
Fig. 2 illustrates the identification process relating ecosystem system and riparian vegetation. This GIS modeling technique of the water bodies by mapping riparian vegetation along the shore not only classify the land cover but also helps to identify the ecosystem services and the relationship between the riparian vegetation and the river ecosystem by economic value calculation of the riparian vegetation along with the water bodies and indication of the state of the ecosystem by macroinvertebrates. In maintaining the ecosystem for the living, the riparian vegetation plays a vital role as it has many societal benefits like habitat and food for wildlife and water bodies. Most importantly, the riparian area serves as an interface between the river and land i.e., upland ecosystem and the water bodies. There is a need to provide land cover geographical information for deploying environment policies implementation. Several relationships exist between the riverine ecosystem and the riparian vegetation, that provides services to the vegetation to the river and the surrounding communities. To understand and protect the ecosystem to provide life support services, there is a need to study the ecosystem. So, it requires a geographical information system (GIS) modeling to be deployed for the study of the ecosystem.

Claims (2)

TECHNIQUE TO GIS MODELLING OF WATER BODIES BY MAPPING RIPARIAN VEGETATION ALONG THE SHORE CLAIMS I/We Claim:
1.High configured smart cameras, sensors and devices captures satellite image of the land cover.
2. High speed wireless internet connection required for data transfer. 3.Computer systems deployed to perform the computation of the algorithms in GIS modeling. 4.Nearest neighbor algorithm deployed to cluster the image data that is collected, and subsets are generated. 5.Cloud platform stores high volume of image data through gateway interface. 6. Machine learning supervised method, Leo Breiman Random Forest classifier deployed for classification 7.Smart display devices deployed to visualize the results of the classification.
TECHNIQUE TO GIS MODELLING OF WATER BODIES BY MAPPING 01 Jan 2021
RIPARIAN VEGETATION ALONG THE SHORE
Drawings 2021100002
Fig. 1. PROCESS FLOW DIAGRAM
Fig.2 GIS MODELLING OF WATER BODIES BY MAPPING RIPARIAN VEGETATION
AU2021100002A 2021-01-01 2021-01-01 Technique to gis modelling of water bodies by mapping riparian vegetation along the shore Ceased AU2021100002A4 (en)

Priority Applications (1)

Application Number Priority Date Filing Date Title
AU2021100002A AU2021100002A4 (en) 2021-01-01 2021-01-01 Technique to gis modelling of water bodies by mapping riparian vegetation along the shore

Applications Claiming Priority (1)

Application Number Priority Date Filing Date Title
AU2021100002A AU2021100002A4 (en) 2021-01-01 2021-01-01 Technique to gis modelling of water bodies by mapping riparian vegetation along the shore

Publications (1)

Publication Number Publication Date
AU2021100002A4 true AU2021100002A4 (en) 2021-03-18

Family

ID=75093479

Family Applications (1)

Application Number Title Priority Date Filing Date
AU2021100002A Ceased AU2021100002A4 (en) 2021-01-01 2021-01-01 Technique to gis modelling of water bodies by mapping riparian vegetation along the shore

Country Status (1)

Country Link
AU (1) AU2021100002A4 (en)

Cited By (1)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN114858987A (en) * 2022-03-30 2022-08-05 河海大学 River and lake water quantity and quality monitoring and management system based on Internet of things

Cited By (2)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN114858987A (en) * 2022-03-30 2022-08-05 河海大学 River and lake water quantity and quality monitoring and management system based on Internet of things
CN114858987B (en) * 2022-03-30 2024-06-11 河海大学 River and lake water quantity and quality monitoring and management system based on Internet of things

Similar Documents

Publication Publication Date Title
D'Addabbo et al. A Bayesian network for flood detection combining SAR imagery and ancillary data
Ghorbani et al. Monitoring offshore oil pollution using multi-class convolutional neural networks
Durgan et al. Unmanned aircraft system photogrammetry for mapping diverse vegetation species in a heterogeneous coastal wetland
Tiwari et al. UAV remote sensing for campus monitoring: a comparative evaluation of nearest neighbor and rule-based classification
AU2021100002A4 (en) Technique to gis modelling of water bodies by mapping riparian vegetation along the shore
Mohan et al. A brief review of recent developments in the integration of deep learning with GIS
Nogueira et al. A tool for bridge detection in major infrastructure works using satellite images
Kabra et al. Deep object detection for waterbird monitoring using aerial imagery
Comert et al. Rapid mapping of forested landslide from ultra-high resolution unmanned aerial vehicle data
Tseng et al. Annual and in-season mapping of cropland at field scale with sparse labels
Stomberg et al. Exploring wilderness characteristics using explainable machine learning in satellite imagery
Azzaoui et al. Detection of crescent sand dunes contours in satellite images using an active shape model with a cascade classifier
Kollár et al. Forest habitat change dynamics in a riparian wetland
Aitkenhead et al. Remote sensing‐based neural network mapping of tsunami damage in Aceh, Indonesia
Mas An artificial neural networks approach to map land use/cover using Landsat imagery and ancillary data
Burrewar et al. A survey on mapping of urban green spaces within remote sensing data using machine learning & deep learning techniques
Cheng et al. Automatic maasailand boma mapping with deep neural networks
White et al. Automated Land Cover Change Detection through Rapid UAS Updates of Digital Surface Models
Lumnitz Mapping urban trees with deep learning and street-level imagery
Herrmann Morphodynamic classification of coastal regions using deep learning through digital imagery collection
Osmólska et al. Using a GEOBIA framework for integrating different data sources and classification methods in context of land use/land cover mapping
Tran et al. Characterising the distribution of mangroves along the southern coast of Vietnam using multi-spectral indices and a deep learning model
Khorram et al. Processing and applications of remotely sensed data
Chang et al. An accuracy comparison for the landslide inventory with the BPNN and SVM methods
Prabu et al. Prediction of land cover changes in Vellore district of Tamil Nadu by using satellite image processing

Legal Events

Date Code Title Description
FGI Letters patent sealed or granted (innovation patent)
MK22 Patent ceased section 143a(d), or expired - non payment of renewal fee or expiry