RESUMEN

Smart forestry, an innovative approach leveraging artificial intelligence (AI), aims to enhance forest management while minimizing the environmental impact. The efficacy of AI in this domain is contingent upon the availability of extensive, high-quality data, underscoring the pivotal role of sensor-based data acquisition in the digital transformation of forestry. However, the complexity and challenging conditions of forest environments often impede data collection efforts. Achieving the full potential of smart forestry necessitates a comprehensive integration of sensor technologies throughout the process chain, ensuring the production of standardized, high-quality data essential for AI applications. This paper highlights the symbiotic relationship between human expertise and the digital transformation in forestry, particularly under challenging conditions. We emphasize the human-in-the-loop approach, which allows experts to directly influence data generation, enhancing adaptability and effectiveness in diverse scenarios. A critical aspect of this integration is the deployment of autonomous robotic systems in forests, functioning both as data collectors and processing hubs. These systems are instrumental in facilitating sensor integration and generating substantial volumes of quality data. We present our universal sensor platform, detailing our experiences and the critical importance of the initial phase in digital transformation-the generation of comprehensive, high-quality data. The selection of appropriate sensors is a key factor in this process, and our findings underscore its significance in advancing smart forestry.

Asunto(s)

RESUMEN

Managed boreal peatlands are widespread and economically important, but they are a large source of greenhouse gases (GHGs). Peatland GHG emissions are related to soil water-table level (WT), which controls the vertical distribution of aerobic and anaerobic processes and, consequently, sinks and sources of GHGs in soils. On forested peatlands, selection harvesting reduces stand evapotranspiration and it has been suggested that the resulting WT rise decreases soil net emissions, while the tree growth is maintained. We monitored soil concentrations of CO2, CH4, N2O and O2 by depth down to 80 cm, and CO2 and CH4 fluxes from soil in two nutrient-rich Norway spruce dominated peatlands in Southern Finland to examine the responses of soil GHG dynamics to WT rise. Selection harvesting raised WT by 14 cm on both sites, on average, mean WTs of the monitoring period being 73 cm for unharvested control and 59 cm for selection harvest. All soil gas concentrations were associated with proximity to WT. Both CH4 and CO2 showed remarkable vertical concentration gradients, with high values in the deepest layer, likely due to slow gas transfer in wet peat. CH4 was efficiently consumed in peat layers near and above WT where it reached sub-atmospheric concentrations, indicating sustained oxidation of CH4 from both atmospheric and deeper soil origins also after harvesting. Based on soil gas concentration data, surface peat (top 25/30 cm layer) contributed most to the soil-atmosphere CO2 fluxes and harvesting slightly increased the CO2 source in deeper soil (below 45/50 cm), which could explain the small CO2 flux differences between treatments. N2O production occurred above WT, and it was unaffected by harvesting. Overall, the WT rise obtained with selection harvesting was not sufficient to reduce soil GHG emissions, but additional hydrological regulation would have been needed.

RESUMEN

The main impetus for the global efforts toward the current digital transformation in almost all areas of our daily lives is due to the great successes of artificial intelligence (AI), and in particular, the workhorse of AI, statistical machine learning (ML). The intelligent analysis, modeling, and management of agricultural and forest ecosystems, and of the use and protection of soils, already play important roles in securing our planet for future generations and will become irreplaceable in the future. Technical solutions must encompass the entire agricultural and forestry value chain. The process of digital transformation is supported by cyber-physical systems enabled by advances in ML, the availability of big data and increasing computing power. For certain tasks, algorithms today achieve performances that exceed human levels. The challenge is to use multimodal information fusion, i.e., to integrate data from different sources (sensor data, images, *omics), and explain to an expert why a certain result was achieved. However, ML models often react to even small changes, and disturbances can have dramatic effects on their results. Therefore, the use of AI in areas that matter to human life (agriculture, forestry, climate, health, etc.) has led to an increased need for trustworthy AI with two main components: explainability and robustness. One step toward making AI more robust is to leverage expert knowledge. For example, a farmer/forester in the loop can often bring in experience and conceptual understanding to the AI pipeline-no AI can do this. Consequently, human-centered AI (HCAI) is a combination of "artificial intelligence" and "natural intelligence" to empower, amplify, and augment human performance, rather than replace people. To achieve practical success of HCAI in agriculture and forestry, this article identifies three important frontier research areas: (1) intelligent information fusion; (2) robotics and embodied intelligence; and (3) augmentation, explanation, and verification for trusted decision support. This goal will also require an agile, human-centered design approach for three generations (G). G1: Enabling easily realizable applications through immediate deployment of existing technology. G2: Medium-term modification of existing technology. G3: Advanced adaptation and evolution beyond state-of-the-art.

Asunto(s)

RESUMEN

Conversion of natural forest to anthropogenic land use systems (LUS) often leads to considerable loss of carbon, however, proper management of these LUS may reverse the trend. A study was conducted in a semi-deciduous forest zone of Côte d'Ivoire to assess soil microbial functioning and soil organic carbon (SOC) stocks in varying tree stands, and to determine whether complex tree stands can mimic the natural forest in terms of these soil attributes. Tree plantations studied were monocultures of teak (Tectona grandis) and full-sun cocoa (Theobroma cacao L.), and a mixture of four tree species (MTS) with Tectona grandis, Gmelina arborea, Terminalia ivoriensis and Terminalia superba. An adjacent natural forest was considered as the reference. Each of these LUS had five replicate stands where soil (0-10 cm depth) samples were taken for physico-chemical parameters and microbial biomass-C (MBC), microbial activities, MBC/SOC ratio and metabolic quotient (qCO2). SOC and total N stocks were also calculated. The C mineralization rate (mg C-CO2 kg-1) and mineral N concentration (mg kg-1) drastically declined in the monocultures of cocoa (154.9 ± 29.3 and 49.8 ± 9.8, respectively) and teak (179.6 ± 27.1 and 54.1 ± 7.3) compared to the natural forest (258.4 ± 21.9 and 108.7 ± 12). However, values in MTS (194.7 ± 24.6 and 105.4 ± 7.4) were not significantly different from those in the natural forest. Similarly, SOC stocks in MTS (28.8 ± 1.9 Mg ha-1) were not significantly different from those recorded in the natural forest (32.9 ± 1.7 Mg ha-1) whereas teak (25.4 ± 1.7 Mg ha-1) and cocoa (23.1 ± 3.4 Mg ha-1) exhibited significantly lower values. Despite the acidic soil and recalcitrant litter conditions, increased MBC/SOC ratio and decreased qCO2 were recorded in the monocrops, suggesting a probable increase in the fungi/bacteria ratio. The complex MTS stand was found to mimic the natural forest in terms of soil microbial activity and organic status, due to the provision of a diversity of litter quality, which may serve as a basis for developing a climate smart timber system in West and Central Africa.

Asunto(s)