South Africa is the leading producer of sugarcane in Africa and one of the largest sugarcane producers in the world. Sugarcane is grown under a wide range of climatic, agronomic, and socio-economic conditions in the country. Stress factors such as water and nutrient deficiencies, and insect pests and diseases are among the most important factors affecting sugarcane production in the country. Monitoring of stress in sugarcane is therefore essential for assessing the consequences on yield and for taking action of their mitigation. The prediction of sugarcane yield, on the other hand is also a significant practice for making informed decisions for effective and sound crop planning and management efforts regarding e.g., milling schedules, marketing, pricing, and cash flows. In South Africa, the detection of stress factors such as nitrogen (N) deficiency and sugarcane thrips (Fulmekiola serrata Kobus) damage and infestation are made using traditional direct methods whereby leaf samples are collected from sugarcane fields and the appropriate laboratory analysis is then performed. These methods are regarded as being time-consuming, labour-intensive, costly, and can be biased as often they are not uniformly applied across sugarcane growing areas in the country. In this regard, the development of systematically organised geo-and time-referenced accurate methods that can detect sugarcane stress factors and predict yields are required. Remote sensing offers near-real-time, potentially inexpensive, quick and repetitive data that could be used for sugarcane monitoring. Processing techniques of such data have recently witnessed more development leading to more effective extraction of information. In this study the aim was to explore the potential use of remote sensing to quantify stress in and predict yield of sugarcane in South Africa. In the first part of this study, the potential use of hyperspectral remote sensing (i.e. with information on many, very fine, contiguous spectral bands) in estimating sugarcane leaf N concentration was examined. The results showed that sugarcane leaf N can be predicted at high accuracy using spectral data collected using a handheld spectroradiometer (ASD) under controlled laboratory and natural field conditions. These positive results prompted the need to test the use of canopy level hyperspectral data in predicting sugarcane leaf N concentration. Using narrow NDVI-based vegetation indices calculated from Hyperion data, sugarcane leaf N concentration could reliably be estimated. In the second part of this study, the focus was on whether leaf level hyperspectral data could detect sugarcane thrips damage and predict the incidence of the insect. The results indicated that specific wavelengths located in the visible region of the electromagnetic spectrum have the highest possibility of detecting sugarcane thrips damage. Thrips counts could also adequately be predicted for younger sugarcane crops (4–5 months). In the final part of this study, the ability of vegetation indices derived from multispectral data (Landsat TM and ETM+) in predicting sugarcane yield was investigated. The results demonstrated that sugarcane yield can be modelled with relatively small error, using a non-linear random forest regression algorithm. Overall, the study has demonstrated the potential of remote sensing techniques to quantify stress in and predict yield of sugarcane. However, it was found that models for detecting a stress factor or predicting yield in sugarcane vary depending on age group, variety, season of sampling, conditions at which spectral data are collected (controlled laboratory or natural field conditions), level at which remotely-sensed data are captured (leaf or canopy levels), and irrigation conditions. The study was conducted in only one study area (the Umfolozi mill supply area) and very few varieties (N12, N19, and NCo 376) were tested. For practical and operational use of remote sensing in sugarcane monitoring, the development of an optimum universal model for detecting factors of stress and predicting yield of sugarcane, therefore, still remains a challenging task. It is recommended that models developed in this study should be tested – or further elaborated – in other South African sugarcane producing areas with growing conditions similar to those under which the predictive models have been developed. Monitoring of sugarcane thrips should also be evaluated using remotely-sensed data at canopy level; and the ability of multispectral sensors other than Landsat TM and ETM+ should be tested for sugarcane yield prediction. / Thesis (Ph.D.)-University of KwaZulu-Natal, Pietermaritzburg, 2010.

The aim of this study was to evaluate potential applications of remote sensing technology in sugarcane agriculture, using the Umfolozi Mill Supply Area as a case study. Several objectives included the evaluation of remotely sensed satellite information for the following applications: mapping of sugarcane areas, identifying sugarcane characteristics including phenology, cultivar and yield, monitoring the sugarcane inventory throughout the milling season and yield prediction. Four Landsat 7 ETM+ (Enhanced Thematic Mapper Plus) images were obtained for the 2001-2002 season. Mapping of sugarcane areas was conducted by .means of unsupervised hierarchical classifications, on three relatively cloud free, Tasseled Cap transformed images. The Brightness, Greenness and Wetness bands for each Tasseled Cap transformed image were combined into a single image for this classification. The investigation into relationships between satellite spectral reflectances and phenology, cultivar and yield involved the cosine of the solar zenith angle (COST) method for atmospheric correction of all four Landsat 7 ETM+ images. Detailed agronomic records and field boundary information, for a selection of sugarcane fields, were used to extract the at-satellite reflectances on a pixel basis . These values were stored in a relational database for analysis. Monitoring of the sugarcane inventory throughout the milling season was conducted by means of unsupervised classifications on the Brightness, Greenness and Wetness bands for each of the four time-step Tasseled Cap transformed images. Accurate field boundary information for all sugarcane fields was used to mask out non-sugarcane areas. The remaining sugarcane areas in each time-step image were then classified by means of unsupervised classification techniques to ascertain the relative proportions of the different land covers, namely: harvested immature and mature sugarcane by visual interpretation of the classification results. The yield forecasting approach utilized a time-step approach in which Vegetation Indices (VIs) were accumulated over different periods or time frames and compared with annual production. VIs were derived from both the National Oceanic and Atmospheric Administration (NOAA) and Landsat 7 ETM+ sensors. Different periods or times were used for each sensor. The results for the mapping of sugarcane areas showed that the mapping accuracies for the large scale grower fields was higher than for the small-scale growers. In both instances, the level of accuracy was below that of the recommended sugar industry mapping standard, namely 1% of the true area. Despite the low mapping accuracies, much benefit could be realized from the map product in terms of identifying new areas of sugarcane expansion. These would require detailed accurate mapping. The results for monitoring of the sugarcane inventory throughout showed that remote sensing, in conjunction with detailed field information, was able to accurately measure the areas harvested in each time-step image. These results may have highly beneficial applications in sugarcane supply management and monitoring. The results for time-step approach to yield forecasting yielded poor results in general. The Landsat derived VIs showed limited potential; however, the data were only available for one season, making it difficult to quantify the impact of climatic conditions on these results. All results for the time-step approach using NOAA data yielded negative results. The results for the investigation into relationships between satellite spectral reflectances and phenology, cultivar and yield showed that that different phenological stages of sugarcane growth were identifiable from Landsat 7 ETM+ at-satellite reflectances. The sugarcane yields and cultivar types were not correlated with the at-satellite reflectances. These results combined with the sugarcane area monitoring may provide valuable information in the management and monitoring of sugarcane supply. / Thesis (M.Sc.)-University of KwaZulu-Natal, Pietermaritzburg, 2004.