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.

Serpentine soils are derived from the weathering of serpentine and ultramafic rocks, which have a high content of ferromagnesian minerals. The high content of heavy metals in serpentine soils alter their physical and chemical properties making them unsuitable for plant growth. There are six serpentine sites in Sri Lanka and the Ussangoda site is on the southern coast in Hambantota. The moisture content, organic matter and cation exchange capacity (CEC) are low in serpentine soils. The available calcium (Ca) content is low and the magnesium (Mg) content is relatively high. The Ca to Mg ratio is 0.60, which is typical for serpentine soils. Two distinct forms of vegetation grow on the Ussangoda serpentine soil. The large plain is covered by stunted, prostrate species with an extensive root system. Patches of shrubs and trees occur on the plains as small islands. The serpentine flora is sharply demarcated from the surrounding non-serpentine flora by their growth habit. The number of plant families and species is lower in the serpentine soil than in the adjacent non-serpentine areas. Four families comprising six species grew only on the serpentine soil. Five species growing in the serpentine soil contained 560-830 ppm of nickel (Ni) in their tissues. Hybanthus enneaspermus had 1800 ppm of nickel. Two species, Vernonia zeylanica and Scolopia acuminata, are endemic to Sri Lanka.

This study was conducted to determine the variability of soil pH, macronutrients and Na contents in long term sugarcanegrowing Alfisols at Sevanagala, South-East of Sri Lanka. The study site included the entire sugarcane-growing area covering its contrasting cropping systems namely, irrigated and rain-fed cultivation on low humic gley (LHG) and reddish brown earth (RBE) soils, and adjacent undisturbed soils. The mean pH of the two soil types was significantly different and ranged from 4.5 to 9.3. Except some soils under rain-fed cultivation with a pH less than 5.5 in RBE soil and a pH greater than 7.5 in LHG soils, pH in all other soils favoured sugarcane growth. Plant available P content of soils were not significantly different among cropping conditions due to its wide variation. In both cropping systems and soil types there were areas with very low to nondetectable P levels. Exchangeable K content was significantly different between LHG and RBE soils with the latter having a mean concentration of 257 mg/ kg that is favourable for sugarcane cultivation. Though, the mean values are higher than the optimum range, there were K deficient patches in the studied area. Soil exchangeable Ca, Mg and Na contents were low in the study area but were significantly higher in LHG soils than in RBE soils contributing to alkalinity in the former soils especially under rain-fed conditions. The sugarcane-growing soils except LHG under rain-fed conditions showed chemical properties similar to undisturbed soils in the area highlighting their buffered nature despite long-term sugarcane cultivation. This study also emphasised the need for site-specific soil fertility management strategies for the Sevanagala sugarcane growing areas.

Some of the largest expanses of ultramafic soils occur in South Asia, but knowledge of the plant diversity and biogeochemistry of these systems in Sri Lanka is very limited. This study aimed to assess the plant diversity and bedrock and foliar chemistry of all known Sri Lankan ultramafic outcrops. The field survey yielded a total of 132 plant taxa from 44 families. The enigmatic nickel hyperaccumulator Rinorea bengalensis (Violaceae), first reported in Sri Lanka over four decades ago, was rediscovered at a newly surveyed ultramafic site, however, it did not hyperaccumulate nickel. No new metal hyperaccumulator plants were identified, suggesting that R. bengalensis is a facultative nickel hyperaccumulator. This study is the first to highlight the floristic diversity of all known Sri Lankan ultramafic outcrops while revealing the facultative nature of nickel and copper hyperaccumulation among some of Sri Lanka's ultramafic plants.

highest ethanol yield (0.0031 %) in non-heat treated bagasse + vinasse medium. Therefore, vinasse and bagasse are potential substrates for bioethanol production. Further studies on process optimisation will enhance the final ethanol yields.