Full Text Available
Note: Clicking the button above will open the full text document at the original institutional repository in a new window.
Indirect soil salinity detection in irregated areas using earth observation methods
Thesis (MSc)--Stellenbosch University, 2017.
Saved in:
| Main Author: | |
|---|---|
| Other Authors: | |
| Format: | Thesis |
| Language: | en_ZA |
| Published: |
Stellenbosch : Stellenbosch University
2017
|
| Subjects: | |
| Tags: |
No Tags, Be the first to tag this record!
|
| _version_ | 1867613880950194176 |
|---|---|
| access_status_str | Open Access |
| author | Muller, Sybrand Jacobus |
| author2 | Van Niekerk, Adriaan |
| author_browse | Muller, Sybrand Jacobus Van Niekerk, Adriaan |
| author_facet | Van Niekerk, Adriaan Muller, Sybrand Jacobus |
| author_sort | Muller, Sybrand Jacobus |
| collection | Thesis |
| dc_rights_str_mv | Stellenbosch University |
| description | Thesis (MSc)--Stellenbosch University, 2017. |
| format | Thesis |
| id | oai:scholar.sun.ac.za:10019.1/101208 |
| institution | Stellenbosch University (South Africa) |
| language | en_ZA |
| last_indexed | 2026-06-10T12:43:10.408Z |
| license_str | Other — see source repository |
| provenance_str_mv | Harvested via OAI-PMH from SUNScholar — Stellenbosch University Repository |
| publishDate | 2017 |
| publishDateRange | 2017 |
| publishDateSort | 2017 |
| publisher | Stellenbosch : Stellenbosch University |
| publisherStr | Stellenbosch : Stellenbosch University |
| record_format | dspace |
| source_str | SUNScholar — Stellenbosch University Repository |
| spelling | oai:scholar.sun.ac.za:10019.1/101208 Indirect soil salinity detection in irregated areas using earth observation methods Muller, Sybrand Jacobus Van Niekerk, Adriaan Stellenbosch University. Faculty of Arts and Social Sciences. Dept. of Geography & Environmental Studies. Soil salinity Salinization Irregated agriculture Remote sensing Landsat satellites Regression analysis Decision trees -- Analysis Supervised classification Machine learning Geographic object-based image analysis Landsat 8 UCTD Thesis (MSc)--Stellenbosch University, 2017. ENGLISH ABSTRACT: Excessive accumulation of salt in the plant root zone has a deteriorating effect on vegetation growth, resulting in reduced crop yield and rendering fertile soil barren, and ultimately leads to decreasing food production. This problem motivates the critical need for active salinity monitoring, with an aim to implement rehabilitation and preventive measures. Conventional salinity monitoring methods, such as regular field visits and laboratory analyses of soil samples, are ineffective for frequent salt accumulation monitoring over large areas. Earth observation techniques can complement conventional methods and potentially improve the cost- and time-efficiency of the regular salt accumulation monitoring. A review of literature identified a number of direct and indirect approaches for detecting accumulated salts using remote sensing. Given that salt accumulation in South Africa is most prevalent in irrigation schemes, the indirect approach, which mainly focusses on salt induced vegetation response, was identified as the preferred approach. Little is known about the optimal combinations of very high resolution satellite imagery and image classification techniques in South African irrigation schemes, where accumulated salt generally occurs in small localized patches. Consequently, two experiments were carried out to: identify suitable spectral and spatial resolutions of imagery; test the value of various image-derived features and classification techniques; and evaluate the spatial scale at which salt accumulation is best identified. The first experiment, applied on an agricultural field scale, analysed WorldView-2 imagery with statistical (regression) and machine learning (decision trees) techniques, and found clear relationships between salt accumulation and image transformations (vegetation indices and image texture). Spatial resolutions of six metres or higher were found to be most suitable. A higher spectral resolution marginally improved classification accuracies, but the increases were insignificant. The second experiment, applied on an irrigation scheme level, assessed SPOT-5 imagery with statistical (regression) and machine learning (various algorithms) techniques in two irrigation schemes. The failure to highlight any consistent image transformation or classification techniques for both irrigation schemes emphasised the negative effect of varying salinity tolerances of crop types and growing phases in identifying salt accumulation. Knowledge gained from the two experiments aided the development of a field level object-based monitoring system that showed sufficient transferability. The quantitative experiments answered key research questions and will serve as a point of departure for future research regarding indirect methods for detecting salt accumulation in agricultural fields. This work will be instrumental in the establishment of a South African salinity monitoring system – with the aim of rehabilitation – and will help to maximize agricultural production and ultimately contribute to sustainable food production. AFRIKAANS OPSOMMING: ’n Oormaat sout in ’n plant se wortelarea het ’n nadelige effek op die plant se groei, veroorsaak ’n afname in oesopbrengs en maak vrugbare grond onvrugbaar, wat uiteindelik tot ’n afname in voedselproduksie lei. Hierdie probleem motiveer die kritiese behoefte aan ’n stelsel wat grondversouting aktief moniteer, met die doel om versoute areas te rehabiliteer en te voorkom. Tradisionele metodes om grondversouting te moniteer sluit gereelde veldwerk en laboratoriumontleding van grondmonsters in, maar is nie vir die gereelde monitering van groot grondversoute-areas effektief nie. Afstandswaarnemingmetodes kan konvensionele metodes aanvul en moontlik tot ’n afname in die tyd en koste verbonde aan die gereelde montering van soutophoping lei. ’n Literatuuroorsig het direkte en indirekte metodes vir die identifisering van grondversouting met behulp van afstandswaarneming uitgelig. Aangesien grondversouting in Suid-Afrika grootliks in besproeiingskemas voorkom, word die indirekte metode, wat die afname in plantegroei as gevolg van grondversouting monitor, verkies. Min inligting is beskikbaar oor die optimale kombinasies van baie hoë resolusie satellietbeelde en beeldklassifikasie-metodes in Suid-Afrikaanse besproeiingskemas, waar grondversouting in klein, gelokaliseerde areas voorkom. Gevolglik is twee eksperimente uitgevoer om geskikte spektrale en ruimtelike resolusies te identifiseer; kenmerke afgelei van beelde en beeldklassifikasie-tegnieke te toets; en die mees geskikte ruimtelike skaal vir die identifisering van grondversouting te evalueer. Die eerste eksperiment, toegepas op ʼn landeryskaal, het WoldView-2 beeldmateriaal met statistiese (regressie) en masjienleer- (beslissingsboom) metodes geanaliseer en het gevind dat daar duidelike verhoudings tussen grondversouting en beeldtransformasies (plantegroeiindeks en beeldtekstuur) bestaan. Ruimtelike resolusies as ses meter of kleiner was as aanvaarbaar beskou. ’n Hoër spektrale resolusie het die resultate effens verbeter, maar was nie betekenisvol nie. Die tweede eksperiment, wat op ’n skema-vlak toegepas was, het SPOT-5-beeldmateriaal met statistiese (regressie) en masjienleermetodes (verskeidenheid algoritmes) op twee verskillende besproeiingskemas geëvalueer. Geen konsekwente beeldtransformasies of -klassifikasies vir die twee studieareas kon uitgelig word nie, wat op die negatiewe effek van die wisselende versoutingstoleransies en verskillende groeistadiums van die gewasse dui. Die kennis wat deur die twee eksperimente opgedoen is, het gelei tot die ontwikkeling van ’n objekgebaseerde-moniteringsisteem op landeryskaal wat voldoende oordraagbaarheid getoon het. Die kwantitatiewe eksperimente het kernnavorsingsvrae beantwoord en sal as ’n vertrekpunt dien vir enige toekomstige navorsing oor die gebruik van indirekte afstandswaarneming metodes vir die identifisering van grondversouting. Die navorsing sal ook bydra tot die vestiging van ’n Suid- Afrikaanse grondversoutingmoniteringsisteem – met die oog op rehabilitasie – wat tot die maksimalisering van landbouproduksie en uiteindelik tot volhoubare voedselproduksie kan lei. Masters 2017-02-21T06:41:04Z 2017-03-29T12:20:37Z 2017-02-21T06:41:04Z 2017-03-29T12:20:37Z 2017-03 Thesis http://hdl.handle.net/10019.1/101208 en_ZA Stellenbosch University xiv, 132 pages application/pdf Stellenbosch : Stellenbosch University |
| spellingShingle | Soil salinity Salinization Irregated agriculture Remote sensing Landsat satellites Regression analysis Decision trees -- Analysis Supervised classification Machine learning Geographic object-based image analysis Landsat 8 UCTD Muller, Sybrand Jacobus Indirect soil salinity detection in irregated areas using earth observation methods |
| title | Indirect soil salinity detection in irregated areas using earth observation methods |
| title_full | Indirect soil salinity detection in irregated areas using earth observation methods |
| title_fullStr | Indirect soil salinity detection in irregated areas using earth observation methods |
| title_full_unstemmed | Indirect soil salinity detection in irregated areas using earth observation methods |
| title_short | Indirect soil salinity detection in irregated areas using earth observation methods |
| title_sort | indirect soil salinity detection in irregated areas using earth observation methods |
| topic | Soil salinity Salinization Irregated agriculture Remote sensing Landsat satellites Regression analysis Decision trees -- Analysis Supervised classification Machine learning Geographic object-based image analysis Landsat 8 UCTD |
| url | http://hdl.handle.net/10019.1/101208 |
| work_keys_str_mv | AT mullersybrandjacobus indirectsoilsalinitydetectioninirregatedareasusingearthobservationmethods |