Options
Rahman, Muhammad
- PublicationEvaluating satellite remote sensing as a method for measuring yield variability in Avocado and Macadamia tree crops(Society of Precision Agriculture Australia (SPAA), 2016)
; ; ; ; - Publication'Sugar from Space': Using Satellite Imagery to Predict Cane Yield and VariabilitySatellite imagery has been demonstrated to be an effective technology for producing accurate pre-harvest estimates in many agricultural crops. For Australian sugarcane, yield forecasting models have been developed from a single date SPOT satellite image acquired around peak crop growth. However, a failure to acquire a SPOT image at this critical growth stage, from continued cloud cover or from competition for the satellite, can prevent an image being captured and therefore a forecast being made for that season. In order to reduce the reliance on a single image capture and to improve the accuracies of the forecasts themselves, time series yield prediction models have been developed for eight sugarcane growing regions using multiple years of free Landsat satellite images. In addition to the forecasting of average regional yield, an automated computational and programming procedure enabling the derivation of crop vigour variability (GNDVI) maps from the freely available Sentinel 2 satellite imagery was developed. These maps, produced for 15 sugarcane growing regions during the 2017 growing season, identify both variations in crop vigour across regions and within every individual crop. These outputs were made available to collaborating mills within each growing region. This paper presents the accuracies achieved from the time series yield forecasting models versus actual 2017 yields for the respective regions, as well as provides an example of the derived mapping outputs.
- PublicationExploring the Potential of High Resolution Satellite Imagery for Yield Prediction of Avocado and Mango Crops(MDPI AG, 2020-04-07)
; ; ; - PublicationA Novel Approach for Sugarcane Yield Prediction Using Landsat Time Series Imagery: A Case Study on Bundaberg RegionQuantifying sugarcane production is critical for a wide range of applications, including crop management and decision making processes such as harvesting, storage, and forward selling. This study explored a novel model for predicting sugarcane yield in Bundaberg region from time series Landsat data. From the freely available Landsat archive, 98 cloud free (<40%) Landsat Thematic Mapper (TM) and Enhanced Thematic Mapper (ETM+) images, acquired between November 15th to July 31st (2001-2015) were sourced for this study. The images were masked using the field boundary layer vector files of each year and the GNDVI was calculated. An analysis of average green normalized difference vegetation index (GNDVI) values from all sugarcane crops grown within the Bundaberg region over the 15 year period identified the beginning of April as the peak growth stage and, therefore, the optimum time for satellite image based yield forecasting. As the GNDVI is an indicator of crop vigor, the model derived maximum GNDVI was regressed against historical sugarcane yield data, which showed a significant correlation with R² = 0.69 and RMSE = 4.2 t/ha. Results showed that the model derived maximum GNDVI from Landsat imagery would be a feasible and a modest technique to predict sugarcane yield in Bundaberg region.
- PublicationAssessing the potential of Sentinel-1 in retrieving mango phenology and investigating its relation to weather in Southern Ghana(International Society of Precision Agriculture (ISPA), 2022-06-29)
; ; The rise in global production of horticultural tree crops over the past few decades is driving technology-based innovation and research to promote productivity and efficiency. Although mango production is on the rise, application of the remote sensing technology is generally limited and the available study on retrieving mango phenology stages specifically, was focused on the application of optical data. We therefore sought to answer the questions; (1) can key phenology stages of mango be retrieved from radar (Sentinel-1) particularly due to the cloud related limitations of optical satellite remote sensing in the tropics? and (2) does weather have any effect on phenology? The study was conducted on a mango farm in the Yilo Krobo Municipal Area of Ghana. Time series analysis for radar vegetation index (RVI) values for 2018 – 2021 was used to retrieve three key phenology stages of mango namely; Start of Season (SoS), Peak of Season (PoS) and End of Season (EoS). Characteristic annual peaks (in April/May for the major season and October/November for the minor season) and troughs (in June/July for the major season and December/January for the minor season) in the phenology trend of mango were identified. Rainfall and temperature explained less than 2% and 14% of the variability respectively in mango phenology. The application of radar remote sensing provides a cutting edge technology in the assessment of mango phenology, particularly in the tropics where cloud cover is a big challenge. This study offers an opportunity for production efficiency in the mango value chain as understanding of the crop's phenology allows growers to manage farm and post-harvest operations.
- PublicationEstimation of fruit load in mango orchards: tree sampling considerations and use of machine vision and satellite imagery(Springer New York LLC, 2019-08)
; ; Walsh, K BIn current best commercial practice, pre-harvest fruit load predictions of mango orchards are provided based on a manual count of fruit number on up to 5% of trees within each block. However, the variability in fruit number per tree (coefficient of variation, CV, from 27 to 93% across ten orchards) was demonstrated to be such that the best case commercial sampling practice was inadequate for reliable estimation (to an error of 54–82 fruit/tree, and percentage error, PE, of 10% at a probability of 0.95). These results highlight the need for alternative methods for estimation of orchard fruit load. Pre-harvest fruit load was estimated for a case study orchard of 469 trees using (i) count of a sample of trees, (ii) in-field machine vision and (iii) correlation to a tree spectral index estimated using high resolution satellite imagery. A count of 5% of trees (23) in the trial orchard resulted in a PE of 31% (error of 37 fruit/tree), with a count of 157 trees required to achieve a PE of 10% (error of 12 fruit/tree). Sampling effort to achieve a PE of 10% was decreased by only 10% by sampling from aspatial k-means tree classifications based on machine vision derived fruit counts of all trees. Clustering based on tree attributes of canopy volume and trunk circumference was not helpful in decreasing sampling effort as these attributes were poorly correlated to fruit load (R² =0.21 and 0.17, respectively). In-field multi-view machine vision-based estimation of fruit load per tree achieved a R²= 0.97 and a RMSE = 14.8 fruit/tree against harvest fruit count per tree for a set of 18 trees (average = 88; SD = 82 fruit/tree), using a faster region convolutional neural network trained the previous season. The relationship between WorldView-3 (WV3) satellite spectral reflectance characteristics of sampled trees and fruit number was characterised by a R² = 0.66 and a RMSE = 56.1 fruit/tree. For this orchard, for which the actual fruit harvest was 56,720 fruit, the estimate based on a manual count of 5% of trees was 47,955 fruit, while estimates based on 20 iterations of stratified sampling (of 5% of trees in each cycle) had variation (SD) of 9597. The machine vision method resulted in an estimate of 53,520 (SD = 1960) fruit and the remote sensing method, 51,944 (SD = 26,300) fruit for the orchard. - PublicationPotential of Time-Series Sentinel 2 Data for Monitoring Avocado Crop PhenologyThe ability to accurately and systematically monitor avocado crop phenology offers significant benefits for the optimization of farm management activities, improvement of crop productivity, yield estimation, and evaluation crops' resilience to extreme weather conditions and future climate change. In this study, Sentinel-2-derived enhanced vegetation indices (EVIs) from 2017 to 2021 were used to retrieve canopy reflectance information that coincided with crop phenological stages, such as flowering (F), vegetative growth (V), fruit maturity (M), and harvest (H), in commercial avocado orchards in Bundaberg, Queensland and Renmark, South Australia. Tukey's honestly significant difference (Tukey-HSD) test after one-way analysis of variance (ANOVA) with EVI metrics (EVImean and EVIslope) showed statistically significant differences between the four phenological stages. From a Pearson correlation analysis, a distinctive seasonal trend of EVIs was observed (R = 0.68 to 0.95 for Bundaberg and R = 0.8 to 0.96 for Renmark) in all 5 years, with the peak EVIs being observed at the M stage and the trough being observed at the F stage. However, a Tukey-HSD test showed significant variability in mean EVI values between seasons for both the Bundaberg and Renmark farms. The variability of the mean EVIs between the two farms was also evident with a p-value < 0.001. This novel study highlights the applicability of remote sensing for the monitoring of avocado phenological stages retrospectively and near-real time. This information not only supports the 'benchmarking' of seasonal orchard performance to identify potential impacts of seasonal weather variation and pest and disease incursions, but when seasonal growth profiles are aligned with the corresponding annual production, it can also be used to develop phenology-based yield prediction models.
- PublicationMulti-temporal landsat algorithms for the yield prediction of sugarcane crops in Australia(Precision Agriculture Association New Zealand, 2017)
; ; Accurate with-in season yield prediction is important for the Australian sugarcane industry as it supports crop management and decision making processes, including those associated with harvest scheduling, storage, milling, and forward selling. In a recent study, a quadratic model was developed from multi-temporal Landsat imagery (30 m spatial resolution) acquired between 2001-2014 (15th November to 31st July) for the prediction of sugarcane yield grown in the Bundaberg region of Queensland, Australia. The resultant high accuracy of prediction achieved from the Bundaberg model for the 2015 and 2016 seasons inspired the development of similar models for the Tully and Mackay growing regions. As with the Bundaberg model, historical Landsat imagery was acquired over a 12 year (Tully) and 10 year (Mackay) period with the capture window again specified to be between 1st November to 30th June to coincide with the sugarcane growing season. All Landsat images were downloaded and processed using Python programing to automate image processing and data extraction. This allowed the model to be applied rapidly over large areas. For each region, the average green normalized difference vegetation index (GNDVI) for all sugarcane crops was extracted from each image and overlayed onto one time scale 1st November to 30th June. Using the quadratic model derived from each regional data set, the maximum GNDVI achieved for each season was calculated and regressed against the corresponding annual average regional sugarcane yield producing strong correlation for both Tully (R2 = 0.89 and RMSE = 5.5 t/ha) and Mackay (R2 = 0.63 and RMSE = 5.3 t/ha). Moreover, the establishment of an annual crop growth profile from each quadratic model has enabled a benchmark of historic crop development to be derived. Any deviation of future crops from this benchmark can be used as an indicator of widespread abiotic or biotic constraints. As well as regional forecasts, the yield algorithms can also be applied at the pixel level to allow individual yield maps to be derived and delivered near real time to all Australian growers and millers. - PublicationIntegrating Landsat-8 and Sentinel-2 Time Series Data for Yield Prediction of Sugarcane Crops at the Block LevelEarly prediction of sugarcane crop yield at the commercial block level (unit area of a single crop of the same variety, ratoon or planting date) offers significant benefit to growers, consultants, millers, policy makers, crop insurance companies and researchers. This current study explored a remote sensing based approach for predicting sugarcane yield at the block level by further developing a regionally specific Landsat time series model and including individual crop sowing (or previous seasons' harvest) date. For the Bundaberg growing region of Australia this extends over a five months period, from July to November. For this analysis, the sugarcane blocks were clustered into 10 groups based on their specific planting or ratoon commencement date within the specified five months period. These clustered or groups of blocks were named 'bins'. Cloud free (<20%) satellite data from the polar-orbiting Landsat-8 (launched 2013), Sentinel-2A (launched 2015) and Sentinel-2B (launched 2017) sensors were acquired over the cane growing region in Bundaberg (area of 32,983 ha), from the growing season starting in July 2014, with the average green normalised difference vegetation index (GNDVI) derived for each block. The number of images acquired for each season was defined by the number of cloud free acquisitions. Using the Simple Linear Machine Learning (ML) algorithm, the extracted Landsat derived GNDVI values for each of the blocks were converted to Sentinel GNDVI. The average GNDVI of each 'bin' was plotted and a quadratic model was fitted through the time series to identify the peak growth stage defined as the maximum GNDVI value. The model derived maximum GNDVI values for each of the bins were then regressed against the average actual yield (t·ha-1) achieved for the respective bin over the five growing years, producing strong correlations (R2 = 0.92 to 0.99). The quadratic curves developed for the different bins were shifted according to the specific planting or ratoon date of an individual block allowing for the peak GNDVI value of the block to be calculated, regressed against the actual block yield (t·ha-1) and the prediction of yield to be made. To validate the accuracies of the 10 time series algorithms representing each of the 10 bins, 592 individual blocks were selected from the Bundaberg region during the 2019 harvest season. The crops were clustered into the appropriate bins with the respective algorithm applied. From a Sentinel image acquired on the 5 May 2019, the prediction accuracies were encouraging (R2 = 0.87 and RMSE = 11.33 (t·ha-1)) when compared to actual harvested yield, as reported by the mill. The results presented in this paper demonstrate significant progress in the accurate prediction of sugarcane yield at the individual sugarcane block level using a remote sensing, time-series based approach.
- PublicationIntegrating Remote Sensing and Weather Variables for Yield Forecasting of Horticultural Tree Crops – A Case Study of Mango in Ghana and Australia(University of New England, 2024-03-08)
; ; ; Globally, the production and trade of fruits and nuts from horticultural tree crops (HTCs) is increasing due to greater demand from a growing world population. Among those HTCs, is the mango, venerated as the “king of fruits” due to its nutritional, health and the economic benefits it provides to both developed and developing nations. Its production and trade have consistently risen since the early 1960s, when official reporting begun. Global production increased from 10.9 million tons in 1961 to over 57 million tons in 2021, representing a 422% increase. According to the Food and Agricultural Organization of the United Nation (FAO), mango contributed USD 0.6 million to approximately USD 3.7 billion from 1961 to 2021 in export value to the global economy.
With increasing food demand, there is the need for increased production, optimizing efficiencies and minimizing environmental impact through the more judicious use of crop inputs. Part of this solution is the development of technologies and analytics that can more accurately and efficiently measure the spatial and temporal variability in tree health, timings of key phenological stages that dictate key management practices and production (yield and quality). The outcomes of these applications also assist with improved decision making around harvest planning and logistics, minimizing potential food wastage along the value chain, market access and forward selling. The current commercial practice for measuring these key parameters in tree crops, including mango, is predominantly by in-field within season assessment which is costly, time and labour intensive, can be inaccurate due to a nonrepresentative area of the orchard being evaluated and human subjectivity.
A review of prior literature identified some recent technological advancements such as the use of weather parameters ‘Growing Degree Days’ for determining tree growth phase and fruit maturation; proximal sensing/ machine vision and the targeted manual fruit counts of individual trees for calibrating remotely sensed imagery. However, these methods are costly, time and labour intensive. Additionally, the approaches can lack spatial granularity, scalability, commercial readiness and provide accuracies fairly similar to current commercial practices. From the publications reviewed across many horticulture and agricultural crops, remote sensing (RS) and associated cutting edge analytics (e.g. Machine learning (ML)) presents as the most likely technology to improve current management and forecasting practices in mango. However, a large knowledge gap still remains.
This study sought to address this knowledge gap by undertaking, four key objectives:
1. Assess the potential of Sentinel-2 satellite data derived vegetation indices (VIs) in distinguishing phenological stages of mango (Chapter 2)
2. Assess the potential of Sentinel-1 satellite data in distinguishing mango phenology and investigating its relationship with weather variables (Chapter 3)
3. Explore the relationship between very high-resolution satellite imagery data and fruit count for predicting mango yield at multiple scales (Chapter 4), and finally
4. Integrate time series remote sensing and weather variables for mango yield prediction using a machine learning approach (Chapter 5).
The study was conducted in commercial mango orchards in both Ghana and Australia covering the period 2015 to 2022 using RS data obtained from platforms such as Sentinel-1 (S1), Sentinel-2 (S2), Landsat-8 and WorldView-2 (WV2) and WorldView-3 (WV3) to derive VIs. A number of Statistical and ML approaches including Linear regression (LR), Random Forest (RF), Support Vector Regression (SVR), eXtreme Gradient Boosting (XGBOOST), Ridge, Least Absolute Shrinkage and Selection Operators (LASSO) and Partial Least Square (PLSR) regressions were employed at various stages throughout the study
Four publications were produced during the study, with the key findings of each publication presented as follows:
• The S2-derived Enhanced Vegetation Index (EVI) was identified as the index that best distinguished five phenological stages of mango (Flowering/Fruitset (F/FS), Fruit Development (FRD), Maturity/Harvesting (M/H), Flushing (FLU) and Dormancy (D)) of four mango farms in Ghana.
• S1-derived radar VI was identified to be responsive for distinguishing three phenological stages (Start of Season (SoS), Peak of Season (PoS) and End of Season (EoS)) from a mango farm in Ghana. These stages align well with three of the key phenological stages (F/FS, M/H and D) retrieved in the optical data (S2) experiment above. It was also established that although weather is known to influence growth and yield of HTCs, for the weather conditions of the study area, its influence on phenology was marginal.
• The evaluation of 24 WV3-derived VIs from individual tree canopies and associated fruit counts collected across many locations, seasons and cultivars (n = 1958), identified no consistent generic relationship between the predictor (24 VIs) and response (fruit count) variables at the individual orchard level. The subsequent modelling of all composite data through ML algorithms, identified the RF-based yield prediction accuracy was better at the farm level than the individual tree level with percentage root mean square error (PRMSE) of 10.1% and 26.5% respectively, for the combined model (i.e. a model trained on all cultivars, locations and seasons data). The potential of developing an ML-based yield variability map at the individual tree level to support precision agriculture was demonstrated.
• An RF-based time series model is capable of predicting block and farm level mango yield around 3 - 5 months ahead of the commencement of the commercial harvest season. The block level combined RS/weather-based RF model for 2021 produced the best result (mean absolute error (MAE) = 2.9 t/ha), marginally better than the RS only RF model (MAE = 3.4 t/ha). The farm level model error (FLEM) was generally lower than the block level model error, for both the combined RS/weather-based RF model (farm = 3.7%, block (NMAE) = 33.6% for 2021) and the RS-based model (farm = 4.3%, block = 38.4% for 2021). The errors thus, ranged from 3.7% to 82.7% and 28.7% to 70.7% at the farm and block levels respectively, for the RS/weather-based RF model across the 8-year time series. Factors such as irregular bearing and data associated limitations were possible causes of errors in the study. The study demonstrated the ability to improve yield prediction accuracy from a finer (e.g. block level) to coarser (e.g. farm level) scales as positive (overprediction) and negative (underprediction) errors tend to cancel out.
Overall, this study demonstrated the potential of integrating RS and weather variables for accurate mango yield prediction. Nevertheless, challenges including a lack of extensive farm level standardized data and the high cost of high-resolution imagery exist. Additionally, whilst these methodologies did demonstrate some benefit over existing practice, further validation of these methodologies is required over more growing locations, cultivars and seasons. This also includes the extrapolation of models at multiple scales, particularly regional and national levels (which were beyond the scope of this study). Furthermore, future research could explore the potential of this method to produce robust estimates in other perennial tree crops.