Arachchige Surantha Ashan Salgadoe

Precision monitoring of crops using drone or unmanned aerial vehicle (UAV) technology is rapidly growing as a climate-smart agriculture practice in rice farming systems in Sri Lanka and globally. In rice fields, the Leaf Color Chart (LCC) is traditionally used for manual comparison of a leaf to the standard LCC categories in the field to determine the fertilizer condition of the plant. However, this lacks autonomous monitoring, rapid monitoring of larger fields, scalability, and the digital transformation of the scores with sprayer drones for targeted fertilizer application. Drones with multispectral cameras could pose a greater rapid and digitalized solution for delineation of leaf color instead of LCC, in the field. Thus, this paper presents a novel attempt of digitization of conventional LCC levels 3 and 4, rice plant leaf greenness levels in the field, with classification and production of a spatial map using drone multispectral images and machine learning algorithms. The experimental setup consisted of ground sampling of LCC levels 3 and 4 from farmer fields and acquisition of drone imagery data above the field with a DJI Phantom 4 Multispectral UAV, from which fifteen vegetation indices related to crop spectra were extracted. The vegetation indices were then employed for training (70%) and testing (30%) with machine learning algorithms: Random Forest (RF), as well as SVM-linear and SVM-RBF, focusing on LCC 3–4 class classification. The results showed good classification performance, with the RF algorithm reporting a test accuracy of 98.2%, outperforming SVM-linear (82.5%) and SVM-RBF (87.5%). The RF model outputs SR, EVI, MSR, NDVI, and TCARI as feature importance indices for the classification of LCC levels 3 and 4 in the rice field. The findings of this proposed method greatly encourage the adaptation of drone technology for real-time monitoring of rice leaf fertilizer levels linked to LCC levels three and four, and spatial identification of the zones across the field. This imposes greater advancement towards climate-smart rice cultivation, targeted fertilizer application and rice field landscape pattern change analysis, underpinning the importance of field digitization.

Late blight, caused by Phytophthora infestans is one of the most devastating diseases in potato cultivation. It results in direct crop losses but also causes a considerable amount of cost for disease management. The primary objective of this study was to investigate P. infestans mating types in selected areas in Sri Lanka and evaluate the risks associated with mating types. In this experiment potato leaves from a range of late blight severity levels were sampled from infected farmer fields. The pathogen was isolated by leaf culture method and confirmed by microscopic observations. The mating types of each isolate were studied by a Metalaxyl sensitivity test. Mating type A1 has been previously reported in Sri Lanka, but mating type A2 was not reported since 2013. Results of this study reveal that mating type A1 was more prominent than A2 (75% and 50% respectively). A2 was reported only from two fields. These observations prove the presence and emergence of mating type A2 in Sri Lankan potato fields. Gradual increase of detectable A2 mating types suggests a high possibility of pathogen inoculum movement between the locations over time. The presence of both mating types raises the possibility of sexual reproduction and generation of oospores. The ratio of A1: A2: (A1+A2) in the current study was 2:1:1. This could permit genetic recombination with the biological evolution of fungicideresistant types of P. infestans species. This study emphasizes the importance of investigations on the mating types to manage late blight disease in Sri Lankan potato fields.

Accurate and timely evaluation of the severity of Potato Late Blight (PLB) is vital in disease control and being confident that fungicides are utilized efficiently. PLB is caused by Phytophthora infestans and is one of the most destructive diseases affecting potatoes. Knowledge gap in determining the severity of the PLB using the Late Blight Key (LBK) results in erroneous disease evaluation, unregulated chemical use, and exorbitant management expenses for PLB. The purpose of this research was to build a novel technique based on smartphones to measure the PLB severity in relation to the LBK. Using a smartphone camera, digital images of sick PLB leaves were taken at a consistent height, and simultaneously the related visual disease severity rating score was recorded using the LBK. The MATLAB (R2019b) image processing toolbox was used to process the photos, which included cropping, manually defining the areas of the leaf and lesion, and determining the pixel ratio (the ratio of PLB lesion to leaf pixels). When data from all the images were merged at the conclusion, regression analysis revealed a virtually perfect linear association (R2=86.6%) between the image-derived pixel ratio and the visual ranking scores of the PLB sickness severity. According to these results, image processing analysis that has been built may precisely identify the leaf areas that are infected with PLB and assess the disease's severity level.

White leaf disease (WLD) is an economically significant disease in the sugarcane industry. This work applied remote sensing techniques based on unmanned aerial vehicles (UAVs) and deep learning (DL) to detect WLD in sugarcane fields at the Gal-Oya Plantation, Sri Lanka. The established methodology to detect WLD consists of UAV red, green, and blue (RGB) image acquisition, the pre-processing of the dataset, labelling, DL model tuning, and prediction. This study evaluated the performance of the existing DL models such as YOLOv5, YOLOR, DETR, and Faster R-CNN to recognize WLD in sugarcane crops. The experimental results indicate that the YOLOv5 network outperformed the other selected models, achieving a precision, recall, mean average precision@0.50 (mAP@0.50), and mean average precision@0.95 (mAP@0.95) metrics of 95%, 92%, 93%, and 79%, respectively. In contrast, DETR exhibited the weakest detection performance, achieving metrics values of 77%, 69%, 77%, and 41% for precision, recall, mAP@0.50, and mAP@0.95, respectively. YOLOv5 is selected as the recommended architecture to detect WLD using the UAV data not only because of its performance, but this was also determined because of its size (14 MB), which was the smallest one among the selected models. The proposed methodology provides technical guidelines to researchers and farmers for conduct the accurate detection and treatment of WLD in the sugarcane fields.

Sugarcane white leaf phytoplasma (white leaf disease) in sugarcane crops is caused by a phytoplasma transmitted by leafhopper vectors. White leaf disease (WLD) occurs predominantly in some Asian countries and is a devastating global threat to sugarcane industries, especially Sri Lanka. Therefore, a feasible and an effective approach to precisely monitoring WLD infection is important, especially at the early pre-visual stage. This work presents the first approach on the preliminary detection of sugarcane WLD by using high-resolution multispectral sensors mounted on small unmanned aerial vehicles (UAVs) and supervised machine learning classifiers. The detection pipeline discussed in this paper was validated in a sugarcane field located in Gal-Oya Plantation, Hingurana, Sri Lanka. The pixelwise segmented samples were classified as ground, shadow, healthy plant, early symptom, and severe symptom. Four ML algorithms, namely XGBoost (XGB), random forest (RF), decision tree (DT), and K-nearest neighbors (KNN), were implemented along with different python libraries, vegetation indices (VIs), and five spectral bands to detect the WLD in the sugarcane field. The accuracy rate of 94% was attained in the XGB, RF, and KNN to detect WLD in the field. The top three vegetation indices (VIs) for separating healthy and infected sugarcane crops are modified soil-adjusted vegetation index (MSAVI), normalized difference vegetation index (NDVI), and excess green (ExG) in XGB, RF, and DT, while the best spectral band is red in XGB and RF and green in DT. The results revealed that this technology provides a dependable, more direct, cost-effective, and quick method for detecting WLD.

The use of satellite-based Remote Sensing (RS) is a well-developed field of research. RS techniques have been successfully utilized to evaluate the chlorophyll content for the monitoring of sugarcane crops. This research provides a new framework for inferring the chlorophyll content in sugarcane crops at the canopy level using unmanned aerial vehicles (UAVs) and spectral vegetation indices processed with multiple machine learning algorithms. Studies were conducted in a sugarcane field located in Sugarcane Research Institute (SRI, Uda Walawe, Sri Lanka), with various fertilizer applications over the entire growing season from 2020 to 2021. An UAV with multispectral camera was used to collect the aerial images to generate the vegetation indices. Ground measurements of leaf chlorophyll were used as indications for fertilizer status in the sugarcane field. Different machine learning (ML) algorithms were used ground-truthing data of chlorophyll content and spectral vegetation indices to forecast sugarcane chlorophyll content. Several machine learning algorithms such as MLR, RF, DT, SVR, XGB, KNN and ANN were applied in two ways: before feature selection (BFS) by training the algorithms with all twenty-four (24) vegetation indices with five (05) spectral bands and after feature selection (AFS) by training algorithms with fifteen (15) vegetation indices. All the algorithms with both BFS and AFS methods were compared with an estimated coefficient of determination (R²) and root mean square error (RMSE). Spectral indices such as RVI and DVI were shown to be the most reliable indices for estimating chlorophyll content in sugarcane fields, with coefficients of determination (R²) of 0.94 and 0.93, respectively. XGB model shows the highest validation score (R²) and lowest RMSE in both methods of BFS (0.96 and 0.14) and AFS (0.98 and 0.78), respectively. However, KNN and SVR algorithms show the lowest validation accuracy than other models. According to the results, the AFS validation score is higher than BFS in MLR, SVR, XGB and KNN. Even though, validation score of the ANN model is decreased in AFS. The findings demonstrated that the use of multispectral UAV could be utilized to estimate chlorophyll content and measure crop health status over a larger sugarcane field. This methodology will aid in real-time crop nutrition management in sugarcane plantations by reducing the need for conventional measurement of sugarcane chlorophyll content.

Accurate pre-harvest yield estimation of high value fruit tree crops provides a range of benefits to industry and growers. Currently, yield estimation in Avocado (Persea americana) and Mango (Mangifera indica) orchards is undertaken by a visual count of a limited number of trees. However, this method is labour intensive and can be highly inaccurate if the sampled trees are not representative of the spatial variability occurring across the orchard. This study evaluated the accuracies of high resolution WorldView (WV) 2 and 3 satellite imagery and targeted field sampling for the pre-harvest prediction of yield. A stratified sampling technique was applied in each block to measure relevant yield parameters from eighteen sample trees representing high, medium and low vigour zones (6 from each) based on classified normalised difference vegetation index (NDVI) maps. For avocado crops, principal component analysis (PCA) and non-linear regression analysis were applied to 18 derived vegetation indices (VIs) to determine the index with the strongest relationship to the measured yield parameters. For mango, an integrated approach of geometric (tree crown area) and optical (spectral vegetation indices) data using artificial neural network (ANN) model produced more accurate predictions. The results demonstrate that accurate maps of yield variability and total orchard yield can be achieved from WV imagery and targeted sampling; whilst accurate maps of fruit size and the incidence of phytophthora can also be achieved in avocado. These outcomes offer improved forecasting than currently adopted practices and therefore offer great benefit to both the avocado and mango industries.