Developing logit calibration model for wildfire smoke characterization based on sentinel-2 multispectral data and machine learning techniques
- Authors: Sali, Athule
- Date: 2023-07
- Subjects: Wildfires -- Prevention and control -- Contracting out , Smoke plumes , Remote-sensing images
- Language: English
- Type: Master's theses , text
- Identifier: http://hdl.handle.net/10353/28467 , vital:74338
- Description: Wildfires are complicated incidents that arise as results of both natural causes and anthropological activities. They have long been regarded as the most devastating phenomena globally. Wildfires are considered a powerful natural factor which has detrimental effect on the global environment. This study was aimed at developing logit calibration models for wildfire smoke prediction based on Sentinel-2 multispectral data and machine learning techniques. Remotely sensed data, in the form of the Sentinel-2 imagery, was used as the base from which wildfire smoke plumes were spectrally characterized and distinguished from clouds and flame using endmember selection. The Smoke Detection Index (SDI) was generated to detect the relative abundance of smoke from the imagery. The Cloud Detection Index (CDI) was also generated from Sentinel-2 imagery to detect the relative abundance of clouds. The bi-level thresholding technique was also used to characterize wildfire smoke from the imagery. The logit models were developed through multilayer perceptron (MLP) neural network to predict wildfire smoke plumes. The Relative Operator Characteristic - Area Under the Curve (ROC-AUC) metrics was used to evaluate the logit models performance. The spectral signature pattern from endmembers revealed that wildfire smoke behaves different across Sentinel-2 multispectral channels with shortwave 1 channel (SWIR-1) exhibiting the highest radiance value. The signature patterns from endmember selection also revealed the distinctive spectral characterization of smoke from those of clouds. The findings showed that whilst smoke exhibited high radiance value on SWIR-1 channel, clouds exhibited high radiance value in the near infrared (NIR), signifying that smoke and cloud are spectrally separatable in the NIR. The smoke-containing pixels from bi-level thresholding were characterized by SDI values that ranged between 0.089 and 0.561. Suggesting that pixels associated with wildfire smoke are limited to this range of values. The logit models developed showed that smoke is predicted in SWIR-2. The ROC-AUC value obtained by this model was 0.77. The Implications emerging from the ROC-AUC results revealed that MLP model employed on the SWIR-2 band present a viable and accurate prediction of wildfire smoke plume. The findings of this study suggest that wildfire smoke is efficiently predicted at the shortwave channels of the electromagnetic spectrum. The wildfire smoke can be spectrally distinguished from cloud in the near infrared channel. , Thesis (MSc) -- Faculty of Science and Agriculture, 2023
- Full Text:
- Date Issued: 2023-07
The effects of exchange rate volatility on manufacturing exports in South Africa
- Authors: Munyu, Yibanati
- Date: 2020-01
- Subjects: Foreign exchange rates
- Language: English
- Type: Master's theses , text
- Identifier: http://hdl.handle.net/10353/20208 , vital:45411
- Description: The study examined the effect of exchange rate volatility on manufacturing exports in South Africa utilizing quarterly time series data from 1990 to 2018. Manufacturing exports (MX), foreign income (GDPf), input costs (C01), the real effective exchange rate (REER) and exchange rate volatility (V) were the key parameters. The study employed two alternative measures of exchange rate volatility. The first measure is the moving average standard deviation of the logarithm of the real effective exchange rate (MASDlnREER) based on the raw monthly data of the real effective exchange rate. The second measure is a dummy variable intended to capture the unexpected variation of the exchange rate. The study utilized the Autoregressive Distributed Lag (ARDL) and the Error Correction Method (ECM) to examine the both the long run and short-run relationships. The empirical results revealed that in the long run, the real effective exchange rate volatility measure (MASDlnREER) has a negative and significant effect on manufacturing exports in South Africa. This result suggests that policy makers need to make an effort to moderate, the volatility of the Rand in an attempt to contain the adverse effects on manufacturing exports. , Thesis (MCom) -- Faculty of Management and Commerce, 2020
- Full Text:
- Date Issued: 2020-01
Analysis of work environment factors as correlate of school management teams' productivity in Mount Frere Education District
- Authors: Majova, L A
- Date: 2016-08
- Subjects: School management teams , School management and organization
- Language: English
- Type: Master's theses , text
- Identifier: http://hdl.handle.net/10353/24684 , vital:63516
- Description: There is a perception that SMTs are not effective in some schools in South Africa. Hence, a huge number of learners in the public schools, particularly in high schools are not getting a good pass in their matric exams. The ineffectiveness of SMTs in some schools results in poor performance, as evidenced in poor matric results ever since 1994 in Mount Frere District, since the end of the homeland system in South Africa. To this end, the study was conducted to analyse work environment factors that affect productivity of school management teams‟ in Mount Frere Education District. Therefore, 64 schools, which formed the sample in this study, were selected randomly from the target of 210 schools (population) in Mount Frere District of Education. It was revealed that the following factors are central to the ineffectiveness of SMTs: lack of knowledge, skills, behaviours and attitudes, Human immune deficiency virus (HIV); redeployment; teachers‟ absenteeism and non-availability and mismanagement of resources. Consequently, the researcher employed quantitative research method to explore the work environment of SMTs in Mount Frere District of Education. To collect data from the SMTs, the SMT Productivity Questionnaire (SPQ) and the SMT performance appraisal form (SPAF) were used. The results were analysed using descriptive statistics like frequency count, percentages, charts and tables, and inferential statistics of Pearson product moment correlation (PPMC). It was discovered that the work environmental factors as espoused by the literature, negatively affect the performance or productivity of SMTs. The findings in the data analysis prove beyond reasonable doubt that redeployment of educators negatively affects the productivity of School Management Teams in various schools. In other words, the study confirmed the literature. , Thesis (MEd) -- Faculty of Education, 2016
- Full Text:
- Date Issued: 2016-08