Digital Transformation in Smart Farm and Forest Operations Needs Human-Centered AI: Challenges and Future Directions.

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.

Environmental life cycle assessment of nano-cellulose and biogas production from manure.

Due to its unique properties, nano fibrillated cellulose (NFC) has been a popular topic of research in recent years. Nevertheless, literature assessing environmental impacts of NFC production is scarce, especially for using other starting materials than wood pulp. Hence, in this study, a new approach of cascaded use of manure to produce biogas and subsequently use the cellulose containing digestate for NFC production (manure scenario) is compared to the production from Kraft pulp from hardwood chips (wood chips scenario) via life cycle assessment (LCA). To produce comparable outputs (NFC and biogas) in both scenarios a typical Austrian biogas plant with maize silage and pig slurry as input material is included in the wood chips scenario. A proxy approach is used to upscale the manure scenario from laboratory to an industrial scale (except for the pulp to NFC step) to ensure comparability of both scenarios. The impact categories global warming potential (GWP), fossil resource scarcity, freshwater eutrophication, human toxicity, terrestrial acidification (TAP) and terrestrial ecotoxicity potential are analysed referring to the functional unit of 1 kg NFC. Results show that the manure scenario has at least 45% lower impacts in all assessed categories. GWP is 4.41 kg CO2 eq./kg NFC in the manure and 9.74 kg CO2 eq./kg NFC in the wood chips scenario. The transformation step from pulp to NFC is identified as environmental hotspot due to the high electricity demand in both scenarios. Results are additionally assessed only for the industrial scale part (includes biogas and pulp production). In the latter the main difference can be found in the substrate production. While it plays a subordinate role in the manure scenario (up to 8%) as manure is seen as a waste stream with no upstream environmental impacts attached, the production of maize silage is one of the hotspots in the industrial part in the wood chips scenario. This difference is especially prominent in TAP, where the substrate production is responsible for 91% of the 0.06 kg SO2 eq. impact, which is tenfold the impact of the manure scenario. This underlines the issue of using energy crops as substrate in biogas plants. It also highlights the importance of further research of using waste streams as inputs for the electricity production and subsequent use in the pulp and paper industry. This LCA demonstrates that NFC production from manure is a sustainable alternative to the production from hardwood Kraft pulp.