A low-cost approach for soil moisture prediction using multi-sensor data and machine learning algorithm

The Science of The Total Environment, Год журнала: 2022, Номер 833, С. 155066 - 155066

Опубликована: Апрель 7, 2022

Язык: Английский

---

Estimating the thermal conductivity of soils using six machine learning algorithms

International Communications in Heat and Mass Transfer, Год журнала: 2022, Номер 136, С. 106139 - 106139

Опубликована: Июнь 14, 2022

Язык: Английский

---

Soil moisture controls over carbon sequestration and greenhouse gas emissions: a review

npj Climate and Atmospheric Science, Год журнала: 2025, Номер 8(1)

Опубликована: Янв. 14, 2025

This literature review synthesizes the role of soil moisture in regulating carbon sequestration and greenhouse gas emissions (CS-GHG). Soil directly affects photosynthesis, respiration, microbial activity, organic matter dynamics, with optimal levels enhancing storage while extremes, such as drought flooding, disrupt these processes. A quantitative analysis is provided on effects CS-GHG across various ecosystems climatic conditions, highlighting a "Peak Decline" pattern for CO₂ at 40% water-filled pore space (WFPS), CH₄ N₂O peak higher (60–80% around 80% WFPS, respectively). The also examines ecosystem models, discussing how dynamics are incorporated to simulate nutrient cycling. Sustainable management practices, including conservation agriculture, agroforestry, optimized water management, prove effective mitigating GHG by maintaining ideal levels. further emphasizes importance advancing multiscale observations feedback modeling through high-resolution remote sensing ground-based data integration, well hybrid frameworks. interactive model-experiment framework emerges promising approach linking experimental model refinement, enabling continuous improvement predictions. From policy perspective, shifting focus from short-term agricultural productivity long-term crucial. Achieving this shift will require financial incentives, robust monitoring systems, collaboration among stakeholders ensure sustainable practices effectively contribute climate mitigation goals.

Язык: Английский

---

Comparison of bagging, boosting and stacking algorithms for surface soil moisture mapping using optical-thermal-microwave remote sensing synergies

CATENA, Год журнала: 2022, Номер 217, С. 106485 - 106485

Опубликована: Июнь 29, 2022

Язык: Английский

---

Features predisposing forest to bark beetle outbreaks and their dynamics during drought

Forest Ecology and Management, Год журнала: 2022, Номер 523, С. 120480 - 120480

Опубликована: Сен. 7, 2022

Climate change is estimated to increase the risk of bark beetle (Ips typographus L.) mass outbreaks in Norway Spruce (Picea abies (L.) Karst) forests. Habitats that are thermally suitable for beetles may expand, and an frequency intensity droughts can promote drought stress on host trees. Drought affects tree vigor unison with environmental features it influences local predisposition forest stands attacks. We aimed study how various influence attacks during a year following years more normal weather conditions but higher populations. included representing stand attributes, topography, soil type wetness, proximity clear-cuts previous attacks, machine learning algorithm (random forest) was applied variation across 48,600 km2 area SE Sweden. Forest increased attack were distinguished high accuracy both conditions. The results show periods, spruce mixed coniferous forests had elevated attack, while mix deciduous trees lower risk. Forests average canopy height strongly predisposed However, similar between height, suggesting periods younger be importance moisture position within landscape highlighted as important year. Identifying areas risk, supported by information control drought, could aid adaptation strategies management intervention efforts. conclude geospatial data have potential further support digitalization industry, facilitating development methods capable quantify dynamics controlling context. Corresponding help direct actions effectively offer decision-making changing climate.

Язык: Английский

---

Groundwater discharge as a driver of methane emissions from Arctic lakes

Nature Communications, Год журнала: 2022, Номер 13(1)

Опубликована: Июнь 27, 2022

Abstract Lateral CH 4 inputs to Arctic lakes through groundwater discharge could be substantial and constitute an important pathway that links production in thawing permafrost atmospheric emissions via lakes. Yet, associated drivers are hitherto poorly constrained because their dynamics spatial variability largely unknown. Here, we unravel the role of for from Spatial patterns across suggest inflows primarily related lake depth wetland cover. Groundwater higher summer than autumn influenced by hydrological (groundwater recharge) biological (CH production). This information on temporal at high northern latitudes is critical predicting warming Arctic, as rising temperatures, increasing precipitation, may further exacerbate

Язык: Английский

---

Different triggers, different stories: Bark-beetle infestation patterns after storm and drought-induced outbreaks

Forest Ecology and Management, Год журнала: 2023, Номер 545, С. 121255 - 121255

Опубликована: Июль 18, 2023

In the recent decades, Norway spruce forests (Picea abies Karst.) in Europe have been subject to large-scale tree mortality caused by bark beetle (Ips typographus L.). The outbreaks were induced storm-felling events and periods of drought, which are becoming increasingly frequent due climate change. Because storms droughts spatially affect differently, infestation patterns configuration beetles might differ between drought. this study, we examined local landscape factors associated with beetle-caused after one storm (2005) drought-induced outbreak (2018), both occurring southern Sweden. A total 13,192 infested one-ha pixels 6,425 drought (in 19,617) compared regarding differences occurrence size forest structures two different outbreaks, using a generalized linear model (GLM) approach. Based on our findings, discovered that allocation patch sizes (including four classes: 5–10, 11–25, 26–50 >50 trees) for quite similar large proportion (>0.6) small groups (≤10 trees). However, outcomes from study demonstrate drivers behind spatial infestations can considerably triggered droughts, main cause seems be linked distribution susceptible trees. most consistent storm-induced increased more volumes area protected (nature reserves) landscape; whereas infestations, clear-cuts heights across scales. Soil moisture mean index (SPEI; May-July) important but generally than may involve time-lagged effect. reasoning during when wind-felled trees removed or not suitable anymore, need find specific standing trees, while all less stressed, results selection dry warm landscapes as they resources favorable reproduction conditions. Finally, show previous influenced later negatively within 25 ha related depletion host These assessment predictions, should integrated future risk mapping outbreaks.

Язык: Английский

---

From Industry 5.0 to Forestry 5.0: Bridging the gap with Human-Centered Artificial Intelligence

Current Forestry Reports, Год журнала: 2024, Номер 10(6), С. 442 - 455

Опубликована: Сен. 11, 2024

Язык: Английский

---

Machine learning based soil maps for a wide range of soil properties for the forested area of Switzerland

Geoderma Regional, Год журнала: 2021, Номер 27, С. e00437 - e00437

Опубликована: Сен. 1, 2021

Spatial soil information in forests is crucial to assess ecosystem services such as carbon storage, water purification or biodiversity. However, spatially continuous on properties at adequate resolution rare forested areas, especially mountain regions. Therefore, we aimed build high-resolution property maps for pH, organic carbon, clay, sand, gravel and density six depth intervals well thickness the entire area of Switzerland. We used legacy data from 2071 profiles evaluated different modelling approaches digital mapping, namely lasso, robust external-drift kriging, geoadditive modelling, quantile regression forest (QRF), cubist support vector machines. Moreover, combined predictions individual models by applying a weighted model averaging approach. All were built large set potential covariates which included e.g. multi-scale terrain attributes remote sensing characterizing vegetation cover. Model performances, against an independent dataset similar all methods. QRF achieved best prediction performance most cases (18 out 37 models), while outperformed five cases. For final therefore predictions. Prediction showed differences properties. While fine earth R2 varied between 0.51 0.64 across intervals, content was more difficult predict (R2 = 0.19–0.32). Since map prediction, assessed 90% derived uncertainty maps. The latter are valuable better interpret provide guidance future mapping campaigns improve

Язык: Английский

---

Trafficability Prediction Using Depth-to-Water Maps: the Status of Application in Northern and Central European Forestry

Current Forestry Reports, Год журнала: 2022, Номер 8(1), С. 55 - 71

Опубликована: Янв. 8, 2022

Abstract Purpose of Review Mechanized logging operations with ground-based equipment commonly represent European production forestry but are well-known to potentially cause soil impacts through various forms disturbances, especially on wet soils low bearing capacity. In times changing climate, shorter periods frozen soils, heavy rain fall events in spring and autumn frequent needs for salvage logging, stakeholders face increasingly unfavourable conditions conduct low-impact operations. Thus, more than ever, planning tools such as trafficability maps required ensure efficient forest at reduced environmental impact. This paper aims describe the status quo existence implementation applied across Europe. addition, focus is given availability accessibility data relevant predictions. Recent Findings A identified method support execution machine-based by prediction areas capacity due conditions. Both topographic wetness index (TWI) depth-to-water algorithm (DTW) used identify produce maps, based spatial information. Summary The input available among governmental institutions some countries already further processed have topography-derived respective enabling technologies hand. Particularly Nordic ahead within this process currently pave way transfer static into dynamic ones, including additional site-specific information received from detailed inventories. Yet, it hoped that a broader adoption these managers throughout Europe will take place enhance sustainable

Язык: Английский

---