Estimation of heavy metal concentrations (Cd and Pb) in plant leaves using optimal spectral indicators and artificial neural networks.

The necessity of continuously monitoring the agricultural products in terms of their health has enforced the development of rapid, low-cost, and non-destructive monitoring solutions. Heavy metal contamination of the plants is known as a source of health threats that are made by their proximities with pollutant soil, water, and air. In this paper, a method was proposed to measure lead (Pb) and cadmium (Cd) contamination of plant leaves through field spectrometry as a low-cost solution for continuous monitoring. The study area was Mahneshan county of Zanjan province in Iran with rich heavy metal mines that have more potential for plant contamination. At first, we collected different plant samples throughout the study area and measured the Pb and Cd concentrations using ICP-AES, in which we observed that the concentrations of Pb and Cd are in the range of 1.4 ~ 282.6 and 0.3 ~ 66.7 µgg-1, respectively, and then we tried to find the optimum estimator model through a multi-objective version of genetic algorithm (GA) optimization that finds simultaneously the structure of an artificial neural network and its input features. The features extracted from the raw spectrums have been collimated to be compatible with the Sentinel-2 multispectral bands for the possibility of further developments. The results demonstrate the efficiency of the optimum estimator model in estimation of the leaves' Pb and Cd contamination, irrespective of the plant type, which has reached the R2 of 0.99 and 0.85 for Pb and Cd, respectively. Additionally, the results suggested that the 783-, 842-, and 865-nm spectral bands, which are similar to the 7, 8, and 8a sentinel-2 spectral bands, are more efficient for this purpose.

Temporal Monitoring and Predicting of the Abundance of Malaria Vectors Using Time Series Analysis of Remote Sensing Data through Google Earth Engine.

In many studies regarding the field of malaria, environmental factors have been acquired in single-time, multi-time or a short-time series using remote sensing and meteorological data. Selecting the best periods of the year to monitor the habitats of Anopheles larvae can be effective in better and faster control of malaria outbreaks. In this article, high-risk times for three regions in Iran, including Qaleh-Ganj, Sarbaz and Bashagard counties with a history of malaria prevalence were estimated. For this purpose, a series of environmental factors affecting the growth and survival of Anopheles were used over a seven-year period through the Google Earth Engine. The results of this study indicated two high-risk times for Qaleh-Ganj and Bashagard counties and three high-risk times for Sarbaz county over the course of a year observing an increase in the abundance of Anopheles mosquitoes. Further evaluation of the results against the entomological data available in previous studies showed that the high-risk times predicted in this study were consistent with an increase in the abundance of Anopheles mosquitoes in the study areas. The proposed method is extremely useful for temporal prediction of the increase in abundance of Anopheles mosquitoes in addition to the use of optimal data aimed at monitoring the exact location of Anopheles habitats.