{"type": "FeatureCollection", "features": [{"id": "10.1016/j.agee.2006.12.005", "type": "Feature", "geometry": null, "properties": {"updated": "2026-07-27T16:15:39Z", "type": "Journal Article", "created": "2007-01-23", "title": "Effects Of Past And Current Disturbance On Carbon Cycling In Grassland Mesocosms", "description": "Abstract   In species rich grasslands, management factors may affect carbon storage both directly (e.g. defoliation) and indirectly, by altering plant community structure. We set up a mesocosm experiment to separate these direct and indirect effects. Monoliths were sampled from two plots of a semi-natural, species-rich pasture at Theix (France), which had been subjected to contrasted disturbance levels, high versus low grazing, for 14 years. These monoliths were placed in transparent enclosures in natural light and temperature conditions. At the start of the experiment, half of the monoliths in each disturbance treatment were shifted to the opposite disturbance regime. Above and below ground CO2 fluxes were then measured continuously over 2 years. The net below ground carbon storage was positively correlated (P", "keywords": ["0106 biological sciences", "2. Zero hunger", "570", "SOL D'HERBAGES", "GRAZING", "04 agricultural and veterinary sciences", "15. Life on land", "SOIL ORGANIC CARBON", "01 natural sciences", "GREENGRASS", "[SDV.EE] Life Sciences [q-bio]/Ecology", " environment", "CARBON SEQUESTRATION", "RESPIRATION", "[SDV.EE]Life Sciences [q-bio]/Ecology", "0401 agriculture", " forestry", " and fisheries", "environment", "PRIMARY PRODUCTIVITY"]}, "links": [{"href": "https://doi.org/10.1016/j.agee.2006.12.005"}, {"rel": "related", "href": "https://repository.soilwise-he.eu/cat/collections/metadata:main/items/Agriculture%2C%20Ecosystems%20%26amp%3B%20Environment", "name": "related record", "description": "related record", "type": "application/json"}, {"rel": "self", "type": "application/geo+json", "title": "10.1016/j.agee.2006.12.005", "name": "item", "description": "10.1016/j.agee.2006.12.005", "href": "https://repository.soilwise-he.eu/cat/collections/metadata:main/items/10.1016/j.agee.2006.12.005"}, {"rel": "collection", "type": "application/json", "title": "Collection", "name": "collection", "description": "Collection", "href": "https://repository.soilwise-he.eu/cat/collections/metadata:main"}], "time": {"date": "2007-06-01T00:00:00Z"}}, {"id": "10.1016/j.agee.2016.12.011", "type": "Feature", "geometry": null, "properties": {"updated": "2026-07-27T16:15:46Z", "type": "Journal Article", "created": "2016-12-12", "title": "Increased Soil Organic Carbon Stocks Under Agroforestry: A Survey Of Six Different Sites In France", "description": "Agroforestry systems are land use management systems in which trees are grown in combination with crops or pasture in the same field. In silvoarable systems, trees are intercropped with arable crops, and in silvopastoral systems trees are combined with pasture for livestock. These systems may produce forage and timber as well as providing ecosystem services such as climate change mitigation. Carbon (C) is stored in the aboveground and belowground biomass of the trees, and the transfer of organic matter from the trees to the soil can increase soil organic carbon (SOC) stocks. Few studies have assessed the impact of agroforestry systems on carbon storage in soils in temperate climates, as most have been undertaken in tropical regions. This study assessed five silvoarable systems and one silvopastoral system in France. All sites had an agroforestry system with an adjacent, purely agricultural control plot. The land use management in the inter-rows in the agroforestry systems and in the control plots were identical. The age of the study sites ranged from 6 to 41 years after tree planting. Depending on the type of soil, the sampling depth ranged from 20 to 100 cm and SOC stocks were assessed using equivalent soil masses. The aboveground biomass of the trees was also measured at all sites. In the silvoarable systems, the mean organic carbon stock accumulation rate in the soil was 0.24 (0.09-0.46) Mg C ha(-1) yr(-1) at a depth of 30 cm and 0.65 (0.004-1.85) Mg C ha(-1) yr(-1) in the tree biomass. Increased SOC stocks were also found in deeper soil layers at two silvoarable sites. Young plantations stored additional SOC but mainly in the soil under the rows of trees, possibly as a result of the herbaceous vegetation growing in the rows. At the silvopastoral site, the SOC stock was significantly greater at a depth of 30-50 cm than in the control. Overall, this study showed the potential of agroforestry systems to store C in both soil and biomass in temperate regions.", "keywords": ["Juglans regia", "F08 - Syst\u00e8mes et modes de culture", "Lolium perenne", "culture associ\u00e9e", "adaptation aux changements climatiques", "01 natural sciences", "630", "http://aims.fao.org/aos/agrovoc/c_6455", "http://aims.fao.org/aos/agrovoc/c_3660", "syst\u00e8me sylvopastoral", "p\u00e2turages", "biomasse a\u00e9rienne des arbres", "[SDV.EE.ECO] Life Sciences [q-bio]/Ecology", " environment/Ecosystems", "[SDV.SA.SDS] Life Sciences [q-bio]/Agricultural sciences/Soil study", "http://aims.fao.org/aos/agrovoc/c_33798", "agroforesterie", "2. Zero hunger", "herbage", "http://aims.fao.org/aos/agrovoc/c_35927", "http://aims.fao.org/aos/agrovoc/c_3539", "Aboveground biomass", "Raphanus sativus", "Helianthus annuus", "04 agricultural and veterinary sciences", "Alley cropping", "rotation culturale", "http://aims.fao.org/aos/agrovoc/c_207", "s\u00e9questration du carbone", "http://aims.fao.org/aos/agrovoc/c_926", "Aboveground", "http://aims.fao.org/aos/agrovoc/c_4182", "Equivalent soil mass", "http://aims.fao.org/aos/agrovoc/c_4060", "Belowground biomass", "http://aims.fao.org/aos/agrovoc/c_4425", "http://aims.fao.org/aos/agrovoc/c_2764", "environment/Ecosystems", "http://aims.fao.org/aos/agrovoc/c_1373987680230", "cycle du carbone", "570", "\u00e9levage extensif", "Triticum aestivum", "Festuca arundinacea", "Brassica", "[SDV.SA.SDS]Life Sciences [q-bio]/Agricultural sciences/Soil study", "Juglans nigra", "utilisation des terres", "arbre d'ombrage", "http://aims.fao.org/aos/agrovoc/c_1374567058134", "http://aims.fao.org/aos/agrovoc/c_1061", "http://aims.fao.org/aos/agrovoc/c_1060", "http://aims.fao.org/aos/agrovoc/c_5626", "http://aims.fao.org/aos/agrovoc/c_3081", "biomasse", "http://aims.fao.org/aos/agrovoc/c_3366", "http://aims.fao.org/aos/agrovoc/c_4059", "0105 earth and related environmental sciences", "http://aims.fao.org/aos/agrovoc/c_2869", "L01 - \u00c9levage - Consid\u00e9rations g\u00e9n\u00e9rales", "http://aims.fao.org/aos/agrovoc/c_16097", "Hordeum", "http://aims.fao.org/aos/agrovoc/c_25548", "15. Life on land", "http://aims.fao.org/aos/agrovoc/c_331583", "Phacelia tanacetifolia", "K10 - Production foresti\u00e8re", "http://aims.fao.org/aos/agrovoc/c_7951", "13. Climate action", "[SDV.EE.ECO]Life Sciences [q-bio]/Ecology", "Sinapis alba", "Soil organic carbon storage", "0401 agriculture", " forestry", " and fisheries", "http://aims.fao.org/aos/agrovoc/c_17299", "http://aims.fao.org/aos/agrovoc/c_6662"]}, "links": [{"href": "https://doi.org/10.1016/j.agee.2016.12.011"}, {"rel": "related", "href": "https://repository.soilwise-he.eu/cat/collections/metadata:main/items/Agriculture%2C%20Ecosystems%20%26amp%3B%20Environment", "name": "related record", "description": "related record", "type": "application/json"}, {"rel": "self", "type": "application/geo+json", "title": "10.1016/j.agee.2016.12.011", "name": "item", "description": "10.1016/j.agee.2016.12.011", "href": "https://repository.soilwise-he.eu/cat/collections/metadata:main/items/10.1016/j.agee.2016.12.011"}, {"rel": "collection", "type": "application/json", "title": "Collection", "name": "collection", "description": "Collection", "href": "https://repository.soilwise-he.eu/cat/collections/metadata:main"}], "time": {"date": "2017-01-01T00:00:00Z"}}, {"id": "10.3168/jds.2019-16575", "type": "Feature", "geometry": null, "properties": {"updated": "2026-07-27T16:21:32Z", "type": "Journal Article", "created": "2019-08-22", "title": "Using machine learning to estimate herbage production and nutrient uptake on Irish dairy farms", "description": "Nutrient management on grazed grasslands is of critical importance to maintain productivity levels, as grass is the cheapest feed for ruminants and underpins these meat and milk production systems. Many attempts have been made to model the relationships between controllable (crop and soil fertility management) and noncontrollable influencing factors (weather, soil drainage) and nutrient/productivity levels. However, to the best of our knowledge not much research has been performed on modeling the interconnections between the influencing factors on one hand and nutrient uptake/herbage production on the other hand, by using data-driven modeling techniques. Our paper proposes to use predictive clustering trees (PCT) learned for building models on data from dairy farms in the Republic of Ireland. The PCT models show good accuracy in estimating herbage production and nutrient uptake. They are also interpretable and are found to embody knowledge that is in accordance with existing theoretical understanding of the task at hand. Moreover, if we combine more PCT into an ensemble of PCT (random forest of PCT), we can achieve improved accuracy of the estimates. In practical terms, the number of grazings, which is related proportionally with soil drainage class, is one of the most important factors that moderates the herbage production potential and nutrient uptake. Furthermore, we found the nutrient (N, P, and K) uptake and herbage nutrient concentration to be conservative in fields that had medium yield potential (11 t of dry matter per hectare on average), whereas nutrient uptake was more variable and potentially limiting in fields that had higher and lower herbage production. Our models also show that phosphorus is the most limiting nutrient for herbage production across the fields on these Irish dairy farms, followed by nitrogen and potassium.", "keywords": ["2. Zero hunger", "nutrient uptake", "Nutrients", "04 agricultural and veterinary sciences", "15. Life on land", "Poaceae", "Animal Feed", "Diet", "Machine Learning", "herbage production", "Dairying", "Milk", "nutrient uptake", " herbage production", " predictive clustering trees", " random forest", "predictive clustering trees", "Animals", "Lactation", "0401 agriculture", " forestry", " and fisheries", "Cattle", "Female", "Ireland", "random forest"]}, "links": [{"href": "https://doi.org/10.3168/jds.2019-16575"}, {"rel": "related", "href": "https://repository.soilwise-he.eu/cat/collections/metadata:main/items/Journal%20of%20Dairy%20Science", "name": "related record", "description": "related record", "type": "application/json"}, {"rel": "self", "type": "application/geo+json", "title": "10.3168/jds.2019-16575", "name": "item", "description": "10.3168/jds.2019-16575", "href": "https://repository.soilwise-he.eu/cat/collections/metadata:main/items/10.3168/jds.2019-16575"}, {"rel": "collection", "type": "application/json", "title": "Collection", "name": "collection", "description": "Collection", "href": "https://repository.soilwise-he.eu/cat/collections/metadata:main"}], "time": {"date": "2019-11-01T00:00:00Z"}}, {"id": "10.5281/zenodo.7307470", "type": "Feature", "geometry": null, "properties": {"license": "Open Access", "updated": "2026-07-27T16:24:42Z", "type": "Dataset", "title": "Soil biological, chemical and physical parameters and herbage yield in a field experiment with organic and inorganic fertilizers on peat grassland in the Netherlands", "description": "Open AccessTo evaluate the performance of organic and inorganic fertilizers for regeneration of ecosystem services in peat grasslands with biodiversity goals, we carried out a field experiment in the western peat district in the Netherlands. The fertilizers tested represent the current practice and potential alternatives for regenerative grassland management on drained peat. <strong>Experimental setup</strong> The field experiment (2013 \u2013 2015) was conducted on a permanent grassland on peat soil (Terric Histosol; SOM 56 g 100 g<sup>\u22121</sup> and pH<sub>KCl</sub> of 4.5 in 0-10 cm) at the experimental dairy farm at Zegveld (the Netherlands). In March 2013, a randomized block experiment (six blocks) was laid out with six fertilizer treatments and a control treatment (no fertilizer: \u201cContr\u201d). The fertilizer used were: conventional dairy cattle slurry manure (\u201cSlurry\u201d), mature compost of kitchen and garden waste (\u201cComp\u201d), dairy cattle farmyard manure (\u201cFYM\u201d), solid fraction of the cattle slurry manure (\u201cSFrac\u201d, obtained by pressurized filtration), inorganic N fertilizer (\u201cIF\u201d; calcium ammonium nitrate, 27% N) and a combination of inorganic N fertilizer and sawdust (\u201cIF+SD\u201d). Plot size was 4 \u00d7 10 m; for the Slurry treatment plots were 5.2 \u00d7 10 m. Slurry was applied by slit injection, the other fertilizers were applied by hand. Target application rate was 120 kg total N ha<sup>\u22121</sup> yr<sup>\u22121</sup>, divided in two applications per year (February/March and May). This is relatively low for conventional grasslands but usual for grasslands with biodiversity goals (Kleijn et al., 2004). The amount of C<sub>total</sub> applied in Comp was taken for the rate of sawdust to be applied. All plots were fertilized with 200 kg K<sub>2</sub>O ha<sup>\u22121</sup> yr<sup>\u22121</sup> (applications in March and May) (Commissie Bemesting Grasland en Voedergewassen, 2019). Fertilizer application quantities and organic matter and nutrient inputs are provided in Fertilizer_intput.csv (dataset). The grassland had an history of conventional management with mainly cutting, winter grazing with sheep and a normal fertilization regime with both slurry manure and inorganic fertilizer. The normal cutting and grazing regime was continued in the first two years of the experiment; during 2015, the monitoring year, the plots were not grazed and only cut for herbage measurements. <strong>Measurements</strong> From April to October 2015, soil and aboveground measurements were carried out. Most soil parameters were measured in October. Earthworms and insect larvae are an important food source for meadow birds during the pre-breeding period in spring (Galbraith, 1989) and were therefore sampled in April. Soil moisture and penetration resistance were measured both in April and October. <em>Soil biological parameters</em> Earthworms and insect larvae were sampled in the top soil layer in two soil cubes (20 \u00d7 20 \u00d7 20 cm) per plot. Earthworms were hand-sorted, counted, weighed and fixed in alcohol prior to identification. Both adults and juveniles were identified to species (Sims and Gerard, 1985; St\u00f6p-Bowitz, 1969) and classified into functional groups (Bouch\u00e9, 1977). Crane flies (Tipulidae; leatherjackets) or click beetles (Elateridae; wireworms) larvae were counted. Phospholipid fatty acids (PLFA) were measured in October. PLFA were extracted from 4 g of fresh soil (Paloj\u00e4rvi, 2006), and analyzed by gas chromatography (Hewlett-Packard, USA). PLFA i15:0, a15:0, 15:0, i16:0, 16:1\u03c99, i17:0, a17:0, cy17:0, 18:1\u03c97 and cy19:0 were chosen to represent bacteria and PLFA 18:2\u03c96 was used as a marker of saprotrophic fungi (Hedlund, 2002). The neutral lipid fatty acid (NLFA) 16:1\u03c95 occurs in storage lipids of arbuscular mycorrhizal fungi (AMF) and was used as marker of AMF (Vestberg et al., 2012). PLFA i15:0, a15:0, i16:0, i17:0 and a17:0 were used as a measure of Gram-positive bacteria, and cy17:0 and cy19:0 for Gram-negative bacteria. PLFA 10Me16:0, 10Me17:0 and 10Me18:0 represented actinomycetes. <em>Soil chemical parameters</em> A soil sample from the 0\u221210 cm layer (c. 50 randomly taken soil cores) per experimental plot was collected in October (auger diameter 2.3 cm; Eijkelkamp grass plot sampler, Giesbeek, the Netherlands), was sieved (1 cm mesh size) and homogenized. One sub-sample was taken for analysis of hot water extractable carbon (HWC) according to Ghani et al. (2003) and one for chemical analysis. Prior to analysis of soil acidity (pH<sub>KCl</sub>), soil organic matter (SOM), total carbon (C<sub>total</sub>), total nitrogen (N<sub>total</sub>), total phosphorus (P<sub>total</sub>) and ammonium-lactate extractable P (P<sub>AL</sub>) by Eurofins Agro (Wageningen, the Netherlands), the sub sample was dried at 40\u00b0C. Soil pH<sub>KCl</sub> was measured according to NEN-ISO 10390 2005. SOM was determined by loss-on-ignition (NEN 5754 2005). C<sub>total</sub> was measured by incineration at 1150\u00b0C, and determination of the CO<sub>2</sub> produced by an infrared detector (LECO Corporation, St. Joseph, Mich., USA). For N<sub>total</sub>, evolved gasses after incineration were reduced to N<sub>2</sub> and measured with a thermal-conductivity detector (LECO Corporation, St. Joseph, Mich., USA). P<sub>total</sub> was analysed with Fleishmann acid (Houba et al., 1997). P<sub>AL</sub> is used to assess the P supply capacity of grassland soils (Reijneveld et al., 2014) and was determined according to Egn\u00e9r et al. (1960) (NEN 5793). <em>Soil physical parameters</em> Soil moisture was determined in April and October in a homogenized 0\u221210 cm soil sample after drying at 105\u00b0C for 24 hrs. Moisture content was expressed as percentage of fresh soil weight. Penetration resistance was measured (April and October) with a penetrologger (Eijkelkamp, Giesbeek, the Netherlands; cone of 2.0 cm<sup>2</sup> penetration surface and 60\u00b0 apex angle. Penetration resistance was expressed as an average of 7 penetrations per plot and per soil layer of 0\u221210, 10\u221220, and 20\u221230 cm. Soil structure and rooting density were assessed in October in the 0\u221210 cm and 10\u221225 cm layers. The percentage of crumbs, sub-angular blocky elements and angular blocky elements was estimated by one experienced person as described by Peerlkamp (1959) and Shepherd (2000), Root density was estimated by scoring visible roots (score 1\u201310; 1 for no roots and 10 for above average). Water infiltration rate was measured in October at three spots per experimental plot in 5 of the 6 blocks (35 plots). A PVC pipe (15 cm high, 15 cm diameter) was pushed into the soil to a depth of 10 cm. 500 ml water was poured into each pipe and the infiltration time was recorded. If the infiltration time exceeded 15 min, the remaining water volume was estimated to calculate the infiltration rate (mm min<sup>\u22121</sup>). <em>Grass yield and botanical composition</em> Grass dry matter (DM) and N yield were determined during 2015 with a Haldrup plot harvester (J. Haldrup a/s, L\u00f8gst\u00f8r, Denmark). The four harvest dates were May 15, June 29, August 19 and September 30. Fresh biomass, DM content (70\u00b0C for 24 hrs) and total N content (Kjeldahl) were determined for each harvest. Herbage DM yield (Mg DM ha<sup>\u22121</sup>) and herbage N yield (kg N ha<sup>\u22121</sup>) were calculated. Apparent N recovery (ANR; kg N.kg N<sup>\u22121</sup>) was calculated as (N yield<sub>(fertilized)</sub> \u2013 N yield<sub>(non-fertilized)</sub>)/(N fertilization rate) (Vellinga and Andr\u00e9, 1999). In June 2015, botanical composition was measured by visually estimating the relative soil cover of the sward and the proportion of each species therein (Sikkema, 1997). <strong>Data files</strong> <em><strong>Data_soil_grass.csv</strong></em> <em>Content:</em> Dataset with soil biological (earthworms, microbial PLFA), soil chemical, soil physical parameters, herbage dry matter and N yields, and botanical parameters. <em>Column names and units:</em> plot: Experimental plot number (1-42) treatment: Treatment code (see text) block: Block number (1-6) EW_species_number: Earthworm - number of species EW_totalnumber: Earthworm - total number per m2 EW_epigeic: Earthworm - number of epigeic adults and juveniles per m2 EW_endogeic: Earthworm - number of endogeic adults and juveniles per m2 EW_adults: Earthworm - number of adults per m2 EW_juveniles: Earthworm - number of juveniles per m2 EW_adult_epigeic: Earthworm - number of epigeic adults per m2 EW_adult_endogeic: Earthworm - number of endogeic adults per m2 EW_juven_epigeic: Earthworm - number of epigeic juveniles per m2 EW_juven_endogeic: Earthworm - number of endogeic juveniles per m2 EW_L_rubellus: Earthworm - number of L. rubellus adults and juveniles per m2 EW_A_chlorotica: Earthworm - number of A. chlorotica adults and juveniles per m2 EW_A_caliginosa: Earthworm - number of A. caliginosa adults and juveniles per m2 EW_O_lacteum: Earthworm - number of O. lacteum adults and juveniles per m2 EW_A_rosea: Earthworm - number of A. rosea adults and juveniles per m2 EW_O_cyaenum: Earthworm - number of O. cyaneum adults and juveniles per m2 EW_L_castaneus: Earthworm - number of L. castaneus adults and juveniles per m2 EW_D_rubida: Earthworm - number of D. rubida adults and juveniles per m2 EW_adult_L_rubellus: Earthworm - number of L. rubellus adults per m2 EW_adult_A_chlorotica: Earthworm - number of A. chlorotica adults per m2 EW_adult_A_caliginosa: Earthworm - number of A. caliginosa adults per m2 EW_adult_O_lacteum: Earthworm - number of O. lacteum adults per m2 EW_adult_A_rosea: Earthworm - number of A. rosea adults per m2 EW_adult_O_cyaenum: Earthworm - number of O. cyaneum adults per m2 EW_adult_L_castaneus: Earthworm - number of L. castaneus adults per m2 EW_adult_D_rubida: Earthworm - number of D. rubida adults per m2 EW_juven_L_rubellus: Earthworm - number of L. rubellus juveniles per m2 EW_juven_A_chlorotica: Earthworm - number of A. chlorotica juveniles per m2 EW_juven_A_caliginosa: Earthworm - number of A. caliginosa juveniles per m2 EW_non_determined: Earthworm - number of non determined individuals per m2 EW_total_biomass: Earthworm - total fresh biomass per m2 Leatherjackets: number of leatherjackets per m2 Wireworms: number of wireworms per m2 TOTmicrPLFA: total microbial PLFA in nmol.g-1 dry soil bactPLFA: bacterial PLFA in nmol.g-1 dry soil saprofungPLFA: saprotrophic fungal PLFA in nmol.g-1 dry soil Fung_bactPLAF_ratio: ratio of fungal to bacterial PLFA GramPLUSplfa: gram positive PLFA in nmol.g-1 dry soil GramMINplfa: gram negative PLFA in nmol.g-1 dry soil ratioGram_PLUS_MIN: ratio of gram positive to gram negative PLFA AMFsporNLFA: AMF spores NLFA in nmol.g-1 dry soil ActinomPLFA: Actinomycetes PLFA in nmol.g-1 dry soil ShannonPLFA: PLFA shannon diversity index SOM: soil organic matter in g.100 g-1 dry soil Ctotal: total C in g.100 g-1 dry soil HWC: hot water extractable C in \u03bcg.100 g-1 dry soil Ntotal: total N in g.100 g-1 dry soil Ptotal: total P2O5 in mg.100 g-1 dry soil P_AL: total P-AL in mg.100 g-1 dry soil pH_KCl: pH-KCl CN_ratio: C:N ratio C_SOM: C:SOM ratio Soilmoisture_April: soil moisture content in April in g.100g-1 fresh soil Penetrationresistance_April_cm010: penetration resistance in April in 10-20 cm in Newton Penetrationresistance_April_cm1020: penetration resistance in April in 20-30 cm in Newton Penetrationresistance_April_cm2030: penetration resistance in April in 0-10 cm in Newton Soilmoisture_October: soil moisture content in October in g.100g-1 fresh soil Penetrationresistance_October_cm010: penetration resistance in October in 10-20 cm in Newton Penetrationresistance_October_cm1020: penetration resistance in October in 20-30 cm in Newton Penetrationresistance_October_cm2030: penetration resistance in October in 0-10 cm in Newton crumb_struct_cm010: percentage of crumb elements in 0-10 cm round_struct_cm011: percentage of sub-angular elements in 0-10 cm rootdensity_cm010: score (1-10) of root density in 0-10 cm crumb_struct_cm1025: percentage of crumb elements in 10-25 cm round_struct_cm1025: percentage of sub-angular elements in 10-25 cm sharp_struct_cm1025: percentage of angular elements in 10-25 cm rootdensity_cm1025: score (1-10) of root density in 10-25 cm water_infiltration: water infiltration rate in mm per minute DM_yield_year: total herbage dry matter yield in kg.ha-1 per year DM_yield_H1: herbage dry matter yield of harvest 1 in kg.ha-1 DM_yield_H2: herbage dry matter yield of harvest 2 in kg.ha-1 DM_yield_H3: herbage dry matter yield of harvest 3 in kg.ha-1 DM_yield_H4: herbage dry matter yield of harvest 4 in kg.ha-1 N_yield_year: total herbage N yield in kg.ha-1 per year N_yield_H1: herbage N yield of harvest 1 in kg.ha-1 N_yield_H2: herbage N yield of harvest 2 in kg.ha-1 N_yield_H3: herbage N yield of harvest 3 in kg.ha-1 N_yield_H4: herbage N yield of harvest 4 in kg.ha-1 DMperc_yield_year: herbage dry matter content (per year; weighed average over the 4 harvests) in g.100g-1 fresh weight DMperc_yield_H1: herbage dry matter content of harvest 1 in g.100g-1 fresh weight DMperc_yield_H2: herbage dry matter content of harvest 2 in g.100g-1 fresh weight DMperc_yield_H3: herbage dry matter content of harvest 3 in g.100g-1 fresh weight DMperc_yield_H4: herbage dry matter content of harvest 4 in g.100g-1 fresh weight Ncontent_yield_year: herbage N content (per year; weighed average over the 4 harvests) in g.kg-1 dry matter Ncontent_yield_H1: herbage N content of harvest 1 in g.kg-1 dry matter Ncontent_yield_H2: herbage N content of harvest 2 in g.kg-1 dry matter Ncontent_yield_H3: herbage N content of harvest 3 in g.kg-1 dry matter Ncontent_yield_H4: herbage N content of harvest 4 in g.kg-1 dry matter fresh_yield_H1: herbvage fresh yield of harvest 1 in Mg.ha-1 ANR: apparent N recovery in kg N.kg N-1 productive_grasses: cover percentage of L. perenne and P trivialis monocotyledons: cover percentage of monocotyledons dicotyledons: cover percentage of dicotyledons plant_species: number of plant species monocot_species: number of monocotyledon species dicot_species: number of dicotyledon species Lolium_perenne: plant cover % Poa_trivialis: plant cover % Phleum_pratense: plant cover % Elytrigia_repens: plant cover % Poa_annua: plant cover % Agrostis_stolonifera: plant cover % Holcus_lanatus: plant cover % Alopecurus_pratensis: plant cover % Alopecurus_geniculatus: plant cover % Trifolium_repens: plant cover % Taraxacum_officinale: plant cover % Ranunculus_arvensis: plant cover % Rumex_obtusifolius: plant cover % Rumex_crispus: plant cover % Ranunculus_acris: plant cover % Stellaria_media: plant cover % Cardamine_pratensis: plant cover % Bellis_perennis: plant cover % Rumex_acetosa: plant cover % Ranunculus_sceleratus: plant cover % Polygonum_aviculare: plant cover % Capsella_bursa-pastoris: plant cover % Glechoma_hederacea: plant cover % Geranium_molle: plant cover % <em><strong>Fertilizer_input.csv</strong></em> <em>Content:</em> Application quantities of fertilizers and ash, organic matter, C and mineral inputs, and fertilizer C:N ratio. Total N input is the sum of mineral N (Nmin) and organic N (Norg). Average values per hectare and per year over the years 2013\u22122015. <em>Column names and units:</em> Treatment: Treatment code (see text) Fertilizer_fresh: Applied fertilizer in Mg.ha<sup>-1</sup> per year (fresh weight) Fertilizer_DM: Applied fertilizer in Mg.ha<sup>-1</sup> per year (dry matter weight); for IF+SD this is the sum of 2.72 Mg sawdust + 0.45 Mg N fertilizer Ash: Mineral fraction in kg.ha<sup>-1</sup> per year OM: Organic matter in kg.ha<sup>-1</sup> per year C: Total C in kg.ha<sup>-1</sup> per year Nmin: Mineral N in kg.ha<sup>-1</sup> per year Norg: Organic N in kg.ha<sup>-1</sup> per year P2O5: kg.ha<sup>-1</sup> per year C_N_ratio: C:N ratio", "keywords": ["2. Zero hunger", "herbage production", "manure", "PLFA", "Life Science", "earthworms", "soil quality", "15. Life on land", "regenerative farming", "6. Clean water"], "contacts": [{"organization": "Deru, Joachim, Bloem, Jaap, De Goede, Ron, Brussaard, Lijbert, Van Eekeren, Nick,", "roles": ["creator"]}]}, "links": [{"href": "https://doi.org/10.5281/zenodo.7307470"}, {"rel": "self", "type": "application/geo+json", "title": "10.5281/zenodo.7307470", "name": "item", "description": "10.5281/zenodo.7307470", "href": "https://repository.soilwise-he.eu/cat/collections/metadata:main/items/10.5281/zenodo.7307470"}, {"rel": "collection", "type": "application/json", "title": "Collection", "name": "collection", "description": "Collection", "href": "https://repository.soilwise-he.eu/cat/collections/metadata:main"}], "time": {"date": "2022-01-01T00:00:00Z"}}, {"id": "11019/1960", "type": "Feature", "geometry": null, "properties": {"updated": "2026-07-27T16:26:08Z", "type": "Journal Article", "created": "2019-08-22", "title": "Using machine learning to estimate herbage production and nutrient uptake on Irish dairy farms", "description": "Nutrient management on grazed grasslands is of critical importance to maintain productivity levels, as grass is the cheapest feed for ruminants and underpins these meat and milk production systems. Many attempts have been made to model the relationships between controllable (crop and soil fertility management) and noncontrollable influencing factors (weather, soil drainage) and nutrient/productivity levels. However, to the best of our knowledge not much research has been performed on modeling the interconnections between the influencing factors on one hand and nutrient uptake/herbage production on the other hand, by using data-driven modeling techniques. Our paper proposes to use predictive clustering trees (PCT) learned for building models on data from dairy farms in the Republic of Ireland. The PCT models show good accuracy in estimating herbage production and nutrient uptake. They are also interpretable and are found to embody knowledge that is in accordance with existing theoretical understanding of the task at hand. Moreover, if we combine more PCT into an ensemble of PCT (random forest of PCT), we can achieve improved accuracy of the estimates. In practical terms, the number of grazings, which is related proportionally with soil drainage class, is one of the most important factors that moderates the herbage production potential and nutrient uptake. Furthermore, we found the nutrient (N, P, and K) uptake and herbage nutrient concentration to be conservative in fields that had medium yield potential (11 t of dry matter per hectare on average), whereas nutrient uptake was more variable and potentially limiting in fields that had higher and lower herbage production. Our models also show that phosphorus is the most limiting nutrient for herbage production across the fields on these Irish dairy farms, followed by nitrogen and potassium.", "keywords": ["2. Zero hunger", "nutrient uptake", "Nutrients", "04 agricultural and veterinary sciences", "15. Life on land", "Poaceae", "Animal Feed", "Diet", "Machine Learning", "herbage production", "Dairying", "Milk", "predictive clustering trees", "Animals", "Lactation", "0401 agriculture", " forestry", " and fisheries", "Cattle", "Female", "Ireland", "random forest"]}, "links": [{"href": "https://doi.org/11019/1960"}, {"rel": "related", "href": "https://repository.soilwise-he.eu/cat/collections/metadata:main/items/Journal%20of%20Dairy%20Science", "name": "related record", "description": "related record", "type": "application/json"}, {"rel": "self", "type": "application/geo+json", "title": "11019/1960", "name": "item", "description": "11019/1960", "href": "https://repository.soilwise-he.eu/cat/collections/metadata:main/items/11019/1960"}, {"rel": "collection", "type": "application/json", "title": "Collection", "name": "collection", "description": "Collection", "href": "https://repository.soilwise-he.eu/cat/collections/metadata:main"}], "time": {"date": "2019-11-01T00:00:00Z"}}], "links": [{"rel": "self", "type": "application/geo+json", "title": "This document as GeoJSON", "href": "https://repository.soilwise-he.eu/cat/collections/metadata:main/items?keywords=herbage&f=json", "hreflang": "en-US"}, {"rel": "alternate", "type": "text/html", "title": "This document as HTML", "href": "https://repository.soilwise-he.eu/cat/collections/metadata:main/items?keywords=herbage&f=html", "hreflang": "en-US"}, {"rel": "collection", "type": "application/json", "title": "Collection URL", "href": "https://repository.soilwise-he.eu/cat/collections/metadata:main", "hreflang": "en-US"}, {"type": "application/geo+json", "rel": "first", "title": "items (first)", "href": "https://repository.soilwise-he.eu/cat/collections/metadata:main/items?keywords=herbage&", "hreflang": "en-US"}, {"rel": "last", "type": "application/geo+json", "title": "items (last)", "href": "https://repository.soilwise-he.eu/cat/collections/metadata:main/items?keywords=herbage&offset=5", "hreflang": "en-US"}], "numberMatched": 5, "numberReturned": 5, "distributedFeatures": [], "timeStamp": "2026-07-27T23:08:13.282773Z"}