A data-driven prediction model for Fennoscandian wildfires

Wildfires are recurrent natural hazards that affect terrestrial ecosystems, the carbon cycle, climate and society. They are typically hard to predict, as their exact location and occurrence are driven by a variety of factors. Identifying a selection of dominant controls can ultimately improve predictions and projections of wildfires in both the current and a future climate. In this study, we applied a data-driven machine learning approach to identify dominant hydrometeorological factors determining fire occurrence over Fennoscandia, and produced spatiotemporally resolved fire danger probability maps. A random forest learner was applied to predict fire danger probabilities over space and time, using a monthly 2001–2019 satellite-based fire occurrence dataset at a 0.25° spatial grid as the target variable. The final data-driven model slightly outperformed the established Canadian fire weather index (FWI) used for comparison. Half of the 30 potential predictors included in the study were automatically selected for the model. Shallow volumetric soil water anomaly stood out as the dominant predictor, followed by predictors related to temperature and deep volumetric soil water. Using a local fire occurrence record for Norway as target data in a separate analysis, the test set performance increased considerably. This improvement shows the potential of developing reliable data-driven prediction models for regions with a high quality fire occurrence record, and the limitation of using satellite-based fire occurrence data in regions subject to small fires not picked up by satellites. We conclude that data-driven fire prediction models are promising, both as a tool to identify the dominant predictors and for fire danger probability mapping. The derived relationships between wildfires and its compound predictors can further be used to assess potential changes in fire danger probability under future climate scenarios.

Soil Mehlich-3 extractable elements as affected by the addition of biochars to a clay soil co-amended with or without a compost

Biochar has potential to sequester carbon and mitigate greenhouse gas emissions, and it may also contribute nutrients for plant growth in temperate climates. Nutrient availability in biochar-amended soil was assessed in a 338-d incubation study. The clay soil prepared with 4% w/w (dry basis) compost or without compost, then amended with wood-based biochar made at different pyrolysis temperatures (maple bark [Acer saccharum] at 400°C [M400], 550°C [M550] and 700°C [M700]) on a dry-rate basis of 5% (w/w). After moistening the soil mixture to 44% volumetric soil water content (equivalent to 70% water-filled pore space), soil mixtures were incubated in the dark at 22°C. Soil was sampled at days 9, 16, 23, 44, 86, 23 170 and 338 of the incubation. Biochar amendment increased the Mehlich-3 P, K, Ca, Mg and Cu concentrations, and reduced the Mehlich-3 Al and Fe concentrations at each sampling date, and M400 had the most significant effect on Mehlich-3 extractable nutrient concentrations. Compost addition also increased the amounts of extractable nutrients. These results suggested that M400 and carbon-rich compost promoted microbial growth and mineralization in amended soil. In addition, soil mixed with compost and amended with biochar had more Mehlich-3 extractable K than when compost or biochar were applied alone, probably due to greater growth and activity of soil K-solubilizing microorganisms. Overall, our study indicated that co-application of wood-based biochar and compost could improve soil fertility in temperate regions by increasing the availability of most plant macronutrients and micronutrients.

Assessing Effects of Salinity on the Performance of a Low-Cost Wireless Soil Water Sensor

Low-cost, accurate soil water sensors combined with wireless communication in an internet of things (IoT) framework can be harnessed to enhance the benefits of precision irrigation. However, the accuracy of low-cost sensors (e.g., based on resistivity or capacitance) can be affected by many factors, including salinity, temperature, and soil structure. Recent developments in wireless sensor networks offer new possibilities for field-scale monitoring of soil water content (SWC) at high spatiotemporal scales, but to install many sensors in the network, the cost of the sensors must be low, and the mechanism of operation needs to be robust, simple, and consume low energy for the technology to be practically relevant. This study evaluated the performance of a resistivity–capacitance-based wireless sensor (Sensoterra BV, 1018LE Amsterdam, Netherlands) under different salinity levels, temperature, and soil types in a laboratory. The sensors were evaluated in glass beads, Oso Flaco sand, Columbia loam, and Yolo clay loam soils. A nonlinear relationship was exhibited between the sensor measured resistance (Ω) and volumetric soil water content (θ). The Ω–θ relationship differed by soil type and was affected by soil solution salinity. The sensor was extremely sensitive at higher water contents with high uncertainty, and insensitive at low soil water content accompanied by low uncertainty. The soil solution salinity effects on the Ω–θ relationship were found to be reduced from sand to sandy loam to clay loam. In clay soils, surface electrical conductivity (ECs) of soil particles had a more dominant effect on sensor performance compared to the effect of solution electrical conductivity (ECw). The effect of temperature on sensor performance was minimal, but sensor-to-sensor variability was substantial. The relationship between bulk electrical conductivity (ECb) and volumetric soil water content was also characterized in this study. The results of this study reveal that if the sensor is properly calibrated, this low-cost wireless soil water sensor has the potential of improving soil water monitoring for precision irrigation and other applications at high spatiotemporal scales, due to the ease of integration into IoT frameworks.

ANALYSIS THE WETTED AREA FOR SUBSURFACE DRIP IRRIGATION IN DIFFERENT SOILS TEXTURE

Subsurface drip irrigation is one of the most efficient systems for management of water. This study is aimed to analysis the wetted area for subsurface drip irrigation system. Several models are developed for predicting the wetted widths and the wetted depths which are very important for designing an optimal irrigation system. HYDRUS/2D is used for predicting the dimensions of wetting patterns numerically by using the two dimensional transient flow of water from a subsurface drip irrigation through sandy loam and loamy sand soils. The wetting patterns from a subsurface drip source are simulated by using the system of United States Department of Agriculture, USDA, the wetting patterns are simulated at different values of applied heads, different diameters of drip, and different values of initial volumetric soil water contents which selected as initial conditions. In this work, greater spreading occurs in loamy sand than sandy loam in vertical and horizontal directions. Moreover, the results showed that the empirical formulas which can be used for estimating the wetting dimensions of wetted width and wetted depth in terms of initial volumetric soil water contents, applied heads, diameters of the drip and times of operation, are good with an average relative error not exceed 3%, so it can be used to assist the designers in irrigation field.

Effect of Heterogeneous Field Conditions on Corn Seeding Depth Accuracy and Uniformity

Optimization of planter performance such as uniform seeding depth is required to maximize crop yield potential. Typically, seeding depth is manually adjusted prior to planting by selecting a row-unit depth and a row-unit downforce to ensure proper seed-soil contact. Once set, row-unit depth and downforce are usually not adjusted again for a field although soil conditions may vary. Optimization of planter performance requires automated adjustments of planter settings to varying soil conditions, but development of precision technologies with such capabilities requires a better understanding of soil-planter interactions. The objective of this study was to evaluate seeding depth response to varying soil conditions between and within fields and to discuss implications for development and implementation of active planting technologies. A 6-row John Deere MaxEmerge Plus planter equipped with heavy-duty downforce springs was used to plant corn ( L.) in central Alabama during the 2014 and 2015 growing seasons. Three depths (4.4, 7.0, and 9.5 cm) and three downforces (corresponding to an additional row-unit weight of 0.0, 1.1, and 1.8 kN) were selected to represent common practices. Depth and downforce were not readjusted between fields and growing seasons. Seeding depth was measured after emergence. Corn seeding depth significantly varied with heterogeneous soil conditions between and within fields and the planter failed to achieve uniform seeding depth across a field. Differences in corn seeding depth between fields and growing seasons were as high as 2.1 cm for a given depth and downforce combination. Corn seeding depth significantly co-varied with field elevation but not with volumetric soil water content. Seeding depth varied with elevation at a rate ranging from -0.1 cm/m to -0.6 cm/m. Seeding depth co-variation to field elevation account for some but not all site-specific seeding depth variability identified within each field trial. These findings provide a better understanding of site-specific seeding depth variability and issues to address for the development of site-specific planting technologies to control seeding depth accuracy and improve uniformity. Keywords: Depth control, Downforce, Planter, Precision agriculture, Seeding depth, Uniformity.