Machine Learning and Soil Humidity Sensing: Signal Strength Approach

The Internet-of-Things vision of ubiquitous and pervasive computing gives rise to future smart irrigation systems comprising the physical and digital worlds. A smart irrigation ecosystem combined with Machine Learning can provide solutions that successfully solve the soil humidity sensing task in order to ensure optimal water usage. Existing solutions are based on data received from the power hungry/expensive sensors that are transmitting the sensed data over the wireless channel. Over time, the systems become difficult to maintain, especially in remote areas due to the battery replacement issues with a large number of devices. Therefore, a novel solution must provide an alternative, cost- and energy-effective device that has unique advantage over the existing solutions. This work explores the concept of a novel, low-power, LoRa-based, cost-effective system that achieves humidity sensing using Deep Learning techniques that can be employed to sense soil humidity with high accuracy simply by measuring the signal strength of the given underground beacon device.

Efficiency of Methodologies Used in the Evaluation of the Weed Seed Bank under Mediterranean Conditions

The objective of this study was to compare the efficiency of two methodologies, seed germination (SG) and seed physical extraction SPE), to assess the weed community from two locations with different soil and climatic conditions: M, with dry and low soil fertility, and S with high soil humidity and fertility. Over three years of study, the analysis of both methodologies confirmed differences in seed bank composition. In M, fewer seeds were recorded by SG than SPE (13.5% and 86.5% respectively), while in S, the difference between percentages was less (31.58% by SG and 68.41% by SPE). Our findings confirmed that Portulaca oleracea L., Amaranthus blitoides S. Watson and Chenopodium album L. were abundantly found in M. Anacyclus clavatus (Def.) Res. seeds were also found, mainly detected by SG. In S, Stellaria media (L.) Vill. was widely found. All species found in S were similarly detected by SG and SPE. The results confirmed that climatic and soil conditions influenced the efficiency of the methodology used to assess the seed bank. M conditions led to an increased seed reservoir, and both methodologies were necessary to obtain the seed bank composition. In S conditions, the seed bank was continuously renewed, and either one of methodologies defined the seed bank composition equally well.

THE APPLICATION OF IOT SOLUTIONS IN GREENHOUSES WITH THE AIM OF REDUCING ELECTRICAL ENERGY CONSUMPTION

In this paper, we will show a prototype of a system designed based on Internet of Things solutions with the aim of optimizing electrical energy consumption in order to achieve desired conditions for the growth and development of plants located in the greenhouse. The physical parameters that this system monitors are temperature, relative humidity, soil humidity and luminescence levels. In this prototype, we have three measurement nodes with the task of collecting parameter data, processing them and sending resulting data, via wireless communication, to a receiver. The receiver forwards data to the application on PC. The application processes the data and displays it to the end user who can choose to automatically or manually control the devices that are inside of the greenhouse. Systems placed inside the greenhouse are heating, irrigation, lighting and ventilation systems.

A new find of Carex bohemica (Cyperaceae) in Kyiv Region (Ukraine)

A new locality of Carex bohemica, a rare species listed in the Red Data Book of Ukraine, is reported. The studied population is located in Kyiv Region within the Divychky site UA0000337 of the Emerald Network in Ukraine (Left-Bank Forest-Steppe). The territory housing the population forms a single contour covering two areas of different soil humidity values. On the area of 30 m2, 95 individuals of C. bohemica were discovered. At the time of observation, all individuals were of the generative age. The identified variants of plant communities with participation of C. bohemica belong to the class Phragmito-Magnocaricetea and are similar to the most communities with this species found in Ukraine. As a threat to existence of this population, increasing participation of alien invasive species-transformers and synanthropic species can be considered. Frequent fires occurring during drought periods also pose significant risks to the survival of this population. Further search for new localities of C. bohemica in the areas with suitable habitats is required.

Thinning decreased soil respiration differently in two dryland Mediterranean forests with contrasted soil temperature and humidity regimes

The effects of a thinning treatment on soil respiration (Rs) were analysed in two dryland forest types with a Mediterranean climate in east Spain: a dry subhumid holm oak forest (Quercus ilex subsp. ballota) in La Hunde; a semiarid postfire regenerated Aleppo pine (Pinus halepensis) forest in Sierra Calderona. Two twin plots were established at each site: one was thinned and the other was the control. Rs, soil humidity and temperature were measured regularly in the field at nine points per plot distributed into three blocks along the slope for 3 years at HU and for 2 years at CA after forest treatment. Soil heterotrophic activity was measured in laboratory on soil samples obtained bimonthly from December 2012 to June 2013 at the HU site. Seasonal Rs distribution gave low values in winter, began to increase in spring before lowering as soil dried in summer. This scenario indicates that with a semiarid climate, soil respiration is controlled by both soil humidity and soil temperature. Throughout the study period, the mean Rs value in the HU C plot was 13% higher than at HU T, and was 26% higher at CA C than the corresponding CA T plot value, being the differences significantly higher in control plots during active growing periods. Soil microclimatic variables explain the biggest proportion of variability for Rs: soil temperature explained 24.1% of total variability for Rs in the dry subhumid forest; soil humidity accounted for 24.6% of total variability for Rs in the semiarid forest. As Mediterranean climates are characterised by wide interannual variability, Rs showed considerable variability over the years, which can mask the effect caused by thinning treatment.

Syntaxonomy and ecological differentiation of the pioneer vegetation of Ukraine Classes: Isoëto-Nanojuncetea, Bidentetea

The studies of the pioneer vegetation of freshwater shorelines of water bodies are of particular interest owing to the specific ecology of these habitats and the short cycle for their development in which periods of flooding and subsequent drainage alternate. Using the methods of phytosociological classification and cluster analysis based on the interpretation of 414 phytosociological relevés, the syntaxonomic structure of the pioneer vegetation of freshwater shorelines of the water bodies of Ukraine has been established that are represented by the phytosociological classes Isoëto-Nanojuncetea and Bidentetea. The class Isoëto-Nanojuncetea includes 8 associations that belong to 2 alliances and 1 order and the class Bidentetea includes 10 associations belonging to 2 alliances and 1 order. Phytocoenoses of both classes are more typical for the Polissia region and the forest-steppe zone of Ukraine, where there are favourable habitats with a flat relief, low degree of dissection and a high level of soil humidity. Using a DCA ordination analysis of associations their position in ecological space was determined. It was established that the main factors of ecological differentiation for Isoëto-Nanojuncetea habitats are soil humidity, soil aeration, nitrogen content, as well as temperature regime. Differentiation in the hyperspace of abiotic factors of the class Bidentetea occurs mainly along the gradients of soil humidity, salt regime and acidity. The ecological distribution of syntaxa of this class is also significantly influenced by the concentration of mineral nitrogen compounds in the soil.