Miniaturised hyperspectral cameras are becoming more easily accessible and smaller, enabling efficient monitoring of agricultural crops using unoccupied aerial systems (UAS). This study’s objectives were to develop and assess the performance of UAS-based hyperspectral cameras in the estimation of quantity and quality parameters of grass sward, including the fresh and dry matter yield, the nitrogen concentration (Ncont) in dry matter (DM), the digestibility of organic matter in DM (the D-value), neutral detergent fibre (NDF), and water-soluble carbohydrates (WSC). Next-generation hyperspectral cameras in visible-near-infrared (VNIR, 400–1000 nm; 224 bands) and shortwave-infrared (SWIR; 900–1700 nm; 224 bands) spectral ranges were used, and they were compared with commonly used RGB and VNIR multispectral cameras. The implemented machine-learning framework identified the most informative predictors of various parameters, and estimation models were then built using a random forest (RF) algorithm for each camera and its combinations. The results indicated accurate estimations; the best normalised root-mean-square errors (NRMSE) were 8.40% for the quantity parameters, and the best NRMSEs for the quality parameters were 7.44% for Ncont, 1% for D-value, 1.24% for NDF, and 12.02% for WSC. The hyperspectral datasets provided the best results, whereas the worst accuracies were obtained using the crop height model and RGB data. The integration of the VNIR and SWIR hyperspectral cameras generally provided the highest accuracies. This study showed for the first time the performance of novel SWIR range hyperspectral UAS cameras in agricultural application.

Multi-species grasslands are reservoirs of biodiversity and provide multiple ecosystem services, including fodder production and carbon sequestration. The provision of these services depends on the control exerted on the biogeochemistry and plant diversity of the system by the interplay of biotic and abiotic factors, e.g., grazing or mowing intensity. Biogeochemical models incorporate a mechanistic view of the functioning of grasslands and provide a sound basis for studying the underlying processes. However, in these models, the simulation of biogeochemical cycles is generally not coupled to simulation of plant species dynamics, which leads to considerable uncertainty about the quality of predictions. Ecological models, on the other hand, do account for biodiversity with approaches adopted from plant demography, but without linking the dynamics of plant species to the biogeochemical processes occurring at the community level, and this hampers the models’ capacity to assess resilience against abiotic stresses such as drought and nutrient limitation. While setting out the state-of-the-art developments of biogeochemical and ecological modelling, we explore and highlight the role of plant diversity in the regulation of the ecosystem processes underlying the ecosystems services provided by multi-species grasslands. An extensive literature and model survey was carried out with an emphasis on technically advanced models reconciling biogeochemistry and biodiversity, which are readily applicable to managed grasslands in temperate latitudes. We propose a roadmap of promising developments in modelling.

The objective of this study is to investigate the potential of novel neural network architectures for measuring the quality and quantity parameters of silage grass swards, using drone RGB and hyperspectral images (HSI), and compare the results with the random forest (RF) method and handcrafted features. The parameters included fresh and dry biomass (FY, DMY), the digestibility of organic matter in dry matter (D-value), neutral detergent fiber (NDF), indigestible neutral detergent fiber (iNDF), water-soluble carbohydrates (WSC), nitrogen concentration (Ncont) and nitrogen uptake (NU); datasets from spring and summer growth were used. Deep pre-trained neural network architectures, the VGG16 and the Vision Transformer (ViT), and simple 2D and 3D convolutional neural networks (CNN) were studied. In most cases, the neural networks outperformed RF. The normalized root-mean-square errors (NRMSE) of the best models were for FY 19% (2104 kg/ha), DMY 21% (512 kg DM/ha), D-value 1.2% (8.6 g/kg DM), iNDF 12% (5.1 g/kg DM), NDF 1.1% (6.2 g/kg DM), WSC 10% (10.5 g/kg DM), Ncont 9% (2 g N/kg DM), and NU 22% (11.9 N kg/ha) using independent test dataset. The RGB data provided good results, particularly for the FY, DMY, WSC and NU. The HSI datasets provided advantages for some parameters. The ViT and VGG provided the best results with the RGB data, whereas the simple 3D-CNN was the most consistent with the HSI data.

The sustainable intensification of farming systems is expected to increase food supply and reduce the negative environmental effects of agriculture. It is also seen as an effective adaptation and mitigation strategy in response to climate change. Our aim is to determine farmers’ and other stakeholders’ views on how higher crop yields can be achieved from their currently low levels. This was investigated in two stakeholder workshops arranged in North Savo, Finland, in 2014 and 2016. The workshop participants, who were organized in discussion groups, considered some agricultural policies to discourage the improvement of crop yields. Policy schemes were seen to support extensification and reduce the motivation for yield improvements. However, the most important means for higher crop yields indicated by workshop participants were improved soil conditions with drainage and liming, in addition to improved crop rotations, better sowing techniques, careful selection of cultivars and forage grass mixtures. Suggested solutions for improving both crop yields and farm income also included optimized use of inputs, focusing production at the most productive fields and actively developed farming skills and knowledge sharing. These latter aspects were more pronounced in 2016, suggesting that farmers’ skills are increasingly being perceived as important.

Monitoring agricultural grass fields is particularly important for meat and milk production in Northern Europe, where three harvests occur during a growing season to maximize yields. Reliable data on forage, including biomass and nitrogen concentration, are essential for making informed decisions regarding seed mixtures, fertilizer rates, and harvest timing. Miniaturized hyperspectral cameras mounted on unmanned aerial systems (UAS) have become increasingly accessible and efficient. These cameras, operating in the visible to near-infrared (VNIR) range, have shown potential in estimating grass sward quantity and feeding quality. Additional advancements in hyperspectral technology have emerged the short-wave infrared (SWIR) range for UAS applications, previously utilized mainly in laboratory and aircraft-based systems. This study aims to explore the potential of VNIR and SWIR hyperspectral UAS-based remote sensing in biomass and nitrogen estimation during primary and re-growth stages. Grass fresh yield and nitrogen concentration prediction models were built after selecting the most significant features from the cameras to cope with the high dimensionality of the data. Using best features and machine learning, both fresh yield and nitrogen concentration were estimated with normalized root mean square error better than 10%. This work contributes to the development of accurate remote sensing techniques, supporting sustainable agricultural practices and climate change studies.

Ilmastonmuutoksen ennustetaan pidentävän kasvukautta ja leudontavan talvia mikä mahdollistaisi laajemman laji- ja lajikevalikoiman myös monivuotisissa nurmissa. Etenkin timoteilajikkeiden yhteydessä puhutaan eteläiseistä ja pohjoisista lajikkeista, joissa eteläisen geeniperimän lisääminen johtaa nopeampaan kasvurytmiin, mutta voi heikentää talvenkestävyyttä. Syysviljoilla talvenkestävyyden ja talven aikana tapahtuvan vernalisaation eli keväistymisen merkitystä alueelle sopien lajikkeiden valintaan on tutkittu pitkään. Sen sijaan nurmikasvien talvehtimisen aikana tapahtuvan keväistymisen merkityksestä talvenkestävyydelle tai satopotentiaaliin ei tunneta. Tässä tutkimuksessa selvitettiin miten syksyn karaistumisolot sekä kasvin perimä vaikuttavat talvenkestävyyden ja keväistymisen etenemiseen sekä sadonmuodostukseen nurmilla. Tulosten perusteella pohditaan miten tulevaisuuden talvehtimisoloihin sopivia nurmikasvilajeja ja –lajikkeita voidaan tunnistaa. Tutkimuksessa kerättiin Viikin pellolta kasvinäytteitä talvien 2009-2013 aikana kuukausittain, joista esitelmässä keskitytään talviin 2011-13. Laboratoriossa ja kasvihuoneella määritettiin kerättyjen timotei-, nurminata- ja englanninraiheinälajikkeiden kylmänkestävyys (LT50), kukintapäivä (HD-heading date), pituus, lehtien ja versojen lukumäärä sekä eri versotyyppien (generatiiviset, korrelliset ei-kukkivat ja vegetatiiviset) määrä kasvustossa. Lisäksi määritettiin ensimmäisen sadon kuiva-ainesato ja eri versotyyppien osuus sadosta. Säädatasta laskettiin karaistumispäivien lukumäärä ja kertynyt lämpösumma syksyllä, havainnoitiin lumipeitteisyys ja sen kesto sekä kasvukauden sääolot. Nurmiheinillä vernalisaatiovaatimuksen havaittiin täyttyvän tammikuuhun mennessä minkä jälkeen kukinta ei enää nopeutunut vaan kasvit olivat täysin keväistyneet. Pohjoisten ja eteläisten timoteilajikkeiden välillä havaittiin eroja alkusyksystä, mutta talven edetessä erot lajikkeiden välisissä kukinta-ajoissa poistuivat. Vernalisaatio vapautti korren pituuskasvun ja satopotentiaalin havaittiin olevan korkeimmillaan heti vernalisaatiovaatimuksen täyttymisen jälkeen tammikuussa. Vernalisaation etenemisen ja kylmänkestävyyden purkautumisen välillä ei sen sijaan havaittu merkittävää yhteyttä. Kylmänkestävyyden kehittymiseen vaikutti eniten syksyn aikana kertyneiden karaistumispäivien lukumäärä sekä lämpösumma. Talvina, jolloin karaistumisaika jäi lyhyeksi, myös hyvin talvenkestävät timoteilajikkeet epäonnistuivat karaistumisessa. Tulokset antavat viitteitä siihen miten nurmikasvilajien ja –lajikkeiden välisiä eroja niiden talvehtimisessa voidaan hyödyntää jalostettaessa muuttuviin ilmasto-oloihin sopivia viljelykasveja.