Machine learning methods for assessing photosynthetic activity: environmental monitoring applications.

Monitoring of the photosynthetic activity of natural and artificial biocenoses is of crucial importance. Photosynthesis is the basis for the existence of life on Earth, and a decrease in primary photosynthetic production due to anthropogenic influences can have catastrophic consequences. Currently, great efforts are being made to create technologies that allow continuous monitoring of the state of the photosynthetic apparatus of terrestrial plants and microalgae. There are several sources of information suitable for assessing photosynthetic activity, including gas exchange and optical (reflectance and fluorescence) measurements. The advent of inexpensive optical sensors makes it possible to collect data locally (manually or using autonomous sea and land stations) and globally (using aircraft and satellite imaging). In this review, we consider machine learning methods proposed for determining the functional parameters of photosynthesis based on local and remote optical measurements (hyperspectral imaging, solar-induced chlorophyll fluorescence, local chlorophyll fluorescence imaging, and various techniques of fast and delayed chlorophyll fluorescence induction). These include classical and novel (such as Partial Least Squares) regression methods, unsupervised cluster analysis techniques, various classification methods (support vector machine, random forest, etc.) and artificial neural networks (multilayer perceptron, long short-term memory, etc.). Special aspects of time-series analysis are considered. Applicability of particular information sources and mathematical methods for assessment of water quality and prediction of algal blooms, for estimation of primary productivity of biocenoses, stress tolerance of agricultural plants, etc. is discussed.

Microalgae cultivation for wastewater treatment and biogas production at Moscow wastewater treatment plant.

The process of cultivation of microalgae on purified and clarified wastewater of Kuryanovo wastewater treatment plants (KWWTP) was studied. The studies were conducted on monoculture (Scenedesmus quadricauda and Chlorella sorokiniana) and on polyculture, the composition of which was formed from microalgae present in the wastewater. The authors created and investigated the columnar photobioreactor (PBR), which acted as a pilot project on the purified and clarified water of KWWTP and allowed the removal of total nitrogen and phosphorus phosphates with an efficiency of up to 90%. The formation of a stable biocenosis from 22 species of algae (with 3-4 dominant species) and 31 species of zooplankton organisms belonging to six systematic subdivisions was recorded. The optimal retention time of the microalgae polyculture for the most effective wastewater treatment has been determined. The conducted studies have shown that the depth of decomposition of ashless matter and the ultimate biogas potential of untreated microalgae biomass is 15% lower than the corresponding values obtained with digestion of activated sludge, which necessitates studies in the field of pretreatment of algal biomass. The paper shows: connections between chlorophyll-a content, algal biomass and fluorescence index F0 and between biomass increment and Fv/Fm value.

Fluorescence induction curves registered from individual microalgae cenobiums in the process of population growth.

Registration of chlorophyll fluorescence induction curves (IC) from individual microalgae cenobiums was performed during Scenedesmus quadricauda culture growth. Emphasis was placed on the analysis of patterns of the slow phase of IC, since these slow fluorescence transitions reflect complex interactions between primary and secondary photosynthetic processes. A classification was performed of the ICs obtained according to the patterns of their slow phase. Four different types of such patterns were distinguished. The microalgae population structure with respect to IC patterns was investigated at different stages of culture growth. The distribution of microalgae cenobiums over the patterns of IC was found to change in accordance with the stage of population development. At the stage of the population growth enhancement, nonmonotonous IC dominated with a high steady-state level of fluorescence. The stage of linear growth was characterized by IC with monotonous decay kinetics and low steady-state level of fluorescence. At the third stage including the phases of growth inhibition, stationary state and the beginning of cell death the population structure was the most heterogeneous, with all IC patterns observed.