Estimation of chlorophyll-a concentration of different seasons in outdoor ponds using hyperspectral imaging

Classification, identification, and growth stage estimation of microalgae based on transmission hyperspectral microscopic imaging and machine learning

A transmission hyperspectral microscopic imager (THMI) that utilizes machine learning algorithms for hyperspectral detection of microalgae is presented. The THMI system has excellent performance with spatial and spectral resolutions of 4 µm and 3 nm, respectively. We performed hyperspectral imaging (HSI) of three species of microalgae to verify their absorption characteristics. Transmission spectra were analyzed using principal component analysis (PCA) and peak ratio algorithms for dimensionality reduction and feature extraction, and a support vector machine (SVM) model was used for classification. The average accuracy, sensitivity and specificity to distinguish one species from the other two species were found to be 94.4%, 94.4% and 97.2%, respectively. A species identification experiment for a group of mixed microalgae in solution demonstrates the usability of the classification method. Using a random forest (RF) model, the growth stage in a phaeocystis growth cycle cultivated under laboratory conditions was predicted with an accuracy of 98.1%, indicating the feasibility to evaluate the growth state of microalgae through their transmission spectra. Experimental results show that the THMI system has the capability for classification, identification and growth stage estimation of microalgae, with strong potential for in-situ marine environmental monitoring and early warning detection applications.

Quantitative estimation of wastewater quality parameters by hyperspectral band screening using GC, VIP and SPA

Water pollution has been hindering the world's sustainable development. The accurate inversion of water quality parameters in sewage with visible-near infrared spectroscopy can improve the effectiveness and rational utilization and management of water resources. However, the accuracy of spectral models of water quality parameters is usually prone to noise information and high dimensionality of spectral data. This study aimed to enhance the model accuracy through optimizing the spectral models based on the sensitive spectral intervals of different water quality parameters. To this end, six kinds of sewage water taken from a biological sewage treatment plant went through laboratory physical and chemical tests. In total, 87 samples of sewage water were obtained by adding different amount of pure water to them. The raw reflectance (R_raw) of the samples were collected with analytical spectral devices. The R_raw-SNV were obtained from the R_raw processed with the standard normal variable. Then, the sensitive spectral intervals of each of the six water quality parameters, namely, chemical oxygen demand (COD), biological oxygen demand (BOD), NH₃-N, the total dissolved substances (TDS), total hardness (TH) and total alkalinity (TA), were selected using three different methods: gray correlation (GC), variable importance in projection (VIP) and set pair analysis (SPA). Finally, the performance of both extreme learning machine (ELM) and partial least squares regression (PLSR) was investigated based on the sensitive spectral intervals. The results demonstrated that the model accuracy based on the sensitive spectral ranges screened through different methods appeared different. The GC method had better performance in reducing the redundancy and the VIP method was better in information preservation. The SPA method could make the optimal trade-offs between information preservation and redundancy reduction and it could retain maximal spectral band intervals with good response to the inversion parameters. The accuracy of the models based on varied sensitive spectral ranges selected by the three analysis methods was different: the GC was the highest, the SPA came next and the VIP was the lowest. On the whole, PLSR and ELM both achieved satisfying model accuracy, but the prediction accuracy of the latter was higher than the former. Great differences existed among the optimal inversion accuracy of different water quality parameters: COD, BOD and TN were very high; TA relatively high; and TDS and TH relatively low. These findings can provide a new way to optimize the spectral model of wastewater biochemical parameters and thus improve its prediction precision.

Retrospective analysis of Chlorophyll-a and its correlation with climate and hydrological variations in Mindu Dam, Morogoro, Tanzania

The measurement of Chlorophyll-a in aquatic systems has usually correlated to harmful algae in water bodies. Harmful algal blooms (HABs) are as a result of massive proliferation of blue-green algae (Cyanobacteria). Harmful algal blooms (HABs) pose threats to both the environment as well as human health, and despite this well-known fact, their monitoring and management are still challenging. Climate change, extreme weather events, and hydrological changes are the main drivers and predicted to benefits HABs dynamics in most parts of the world. In Tanzania, studies of HABs proliferation and their possible correlation with variability in climate and hydrology still lag behind despite high demand for developing predicting tools and prevention of HABs proliferation. The present study reports on the retrospective analysis of HABs variation in Mindu Dam located in Morogoro, Tanzania using remote sensing techniques. In the present study comparison between in situ measurement and ocean color (OC2) Chlorophyll-a with the surface reflectance's (band and band combinations) of Landsat 7 and Landsat 8 Operational Land Imager (OLI), was performed. Another approach involved searching for patterns and trends, and teleconnection between Chlorophyll-a index (best band ration) and the climate and hydrological variations in the catchment. The findings demonstrated that minimum and maximum temperatures, solar radiation, Chlorophyll-a concentration registered significant increasing trends. Wind speed and directions, water levels for Mindu Dam showed a significant decreasing trend. On the other hand, rainfall showed no trend. The patterns suggest that there are link and causality between the HABs variations and meteorological parameters such as temperatures, solar radiations, and water levels. The study, therefore, contributes to the application of recent advances in remote sensing and retrospectively analysis of bloom dynamics and search for their link with climate and hydrological changes.

Tea cultivar classification and biochemical parameter estimation from hyperspectral imagery obtained by UAV

It is generally feasible to classify different species of vegetation based on remotely sensed images, but identification of different sub-species or even cultivars is uncommon. Tea trees (Camellia sinensis L.) have been proven to show great differences in taste and quality between cultivars. We hypothesize that hyperspectral remote sensing would make it possibly to classify cultivars of plants and even to estimate their taste-related biochemical components. In this study, hyperspectral data of the canopies of tea trees were collected by hyperspectral camera mounted on an unmanned aerial vehicle (UAV). Tea cultivars were classified according to the spectral characteristics of the tea canopies. Furthermore, two major components influencing the taste of tea, tea polyphenols (TP) and amino acids (AA), were predicted. The results showed that the overall accuracy of tea cultivar classification achieved by support vector machine is higher than 95% with proper spectral pre-processing method. The best results to predict the TP and AA were achieved by partial least squares regression with standard normal variant normalized spectra, and the ratio of TP to AA—which is one proven index for tea taste—achieved the highest accuracy (R_CV = 0.66, RMSE_CV = 13.27) followed by AA (R_CV = 0.62, RMSE_CV = 1.16) and TP (R_CV = 0.58, RMSE_CV = 10.01). The results indicated that classification of tea cultivars using the hyperspectral remote sensing from UAV was successful, and there is a potential to map the taste-related chemical components in tea plantations from UAV platform; however, further exploration is needed to increase the accuracy.