Detection of reed using cnn method and analysis of the dry reed (phragmites australis) for a sustainable lake area

Abstract

Abstract Background Common reed (Phragmites australis L.) is a highly productive wetland plant and a possible valuable resource of renewable biomass worldwide. For a sustainable management the exploitation of reed is beneficial because the increasing demand for sustainable biomass which presents reed bed areas and wetlands. Knowing the properties of plant biomass obtained from reeds is essential both for the effect on combustion equipment and for the impact on the environment. Brates Lake, situated in Galati, Romania is a natural watershed with reed plantations. Results We used the convolutional neural network method combined with the cropped image techniques represent a powerful tool for high-precision image-based biomass detection in lake areas. The study aimed to investigate the morphological and chemical parameters through SEM–EDX analysis and pH, conductivity, nitrate anion, nitrite anion, total nitrogen, sulphate anion, sulphide anion, phosphate anion concentrations were determined from reed extract. The samples have a moderately acidic reaction pH 4.91–4.98. The number of soluble salts in the reed extract is in the range of 3.24–4.70 g/L, the values are within normal limits, providing the plant with the necessary nutrients. Conclusions This is the first time that neural networks are used for the detection and prediction of areas at risk for biodiversity (reduction of water gloss until it disappears, imbalances caused by keeping reeds dry in water) caused by the aggressive and uncontrolled growth of reeds.

Keywords

• Biomass
• Reed
• Convolutional neural networks
• Sustainable