Interior Alaska has a short growing season of 110 d.The knowledge of timings of crop flowering and maturity will provide the information for the agricultural decision making.In this study,six machine learning algorith...Interior Alaska has a short growing season of 110 d.The knowledge of timings of crop flowering and maturity will provide the information for the agricultural decision making.In this study,six machine learning algorithms,namely Linear Discriminant Analysis(LDA),Support Vector Machines(SVMs),k-nearest neighbor(kNN),Naïve Bayes(NB),Recursive Partitioning and Regression Trees(RPART),and Random Forest(RF),were selected to forecast the timings of barley flowering and maturity based on the Alaska Crop Datasets and climate data from 1991 to 2016 in Fairbanks,Alaska.Among 32 models fit to forecast flowering time,two from LDA,12 from SVMs,four from NB,three from RF outperformed models from other algorithms with the highest accuracy.Models from kNN performed worst to forecast flowering time.Among 32 models fit to forecast maturity time,two models from LDA outperformed the models from other algorithms.Models from kNN and RPART performed worst to forecast maturity time.Models from machine learning methods also provided a variable importance explanation.In this study,four out of six algorithms gave the same variable importance order.Sowing date was the most important variable to forecast flowering but less important variable to forecast maturity.The daily maximum temperature may be more important than daily minimum temperature to fit flowering models while daily minimum temperature may be more important than daily maximum temperature to fit maturity models.The results indicate that models from machine learning provide a promising technique in forecasting the timings of flowering and maturity of barley.展开更多
[Objectives]This study was conducted to reveal the characteristics of nutrient absorption and accumulation in Pinus massoniana plantations in Northwestern Guangxi.[Methods]Based on field investigation and indoor analy...[Objectives]This study was conducted to reveal the characteristics of nutrient absorption and accumulation in Pinus massoniana plantations in Northwestern Guangxi.[Methods]Based on field investigation and indoor analysis,the contents,accumulation and annual net accumulation of five nutrient elements(N,P,K,Ca and Mg)in a mature P.massoniana plantation(26-year-old)in Nandan County,Guangxi Province were studied.[Results]The contents of nutrient elements in different organs of the mature P.massoniana plantation were the highest in the leaves,followed by the bark,branch and root,and the lowest in the stem.In general,among the contents of the five elements in different organs,N content was the highest,followed by K or Ca,and P and Mg were the lowest.The total accumulation of nutrient elements in the 26-year-old mature P.massoniana plantation in northwestern Guangxi was 1 384.05 kg/hm^2.Among the different structural levels of the stand,the tree layer had the highest accumulation of nutrient elements,which was 1 198.41 kg/hm^2,accounting for 86.59%of the total accumulation of nutrients in the plantation,and the accumulation of nutrients in other layers from the largest to the smallest was the litter layer(91.97 kg/hm^2),herb layer(49.86 kg/hm^2)and shrub layer(43.92 kg/hm^2),accounting for 3.17%,3.60%and 6.64%of the total nutrient accumulation of the plantation,respectively.The annual net accumulation of nutrient elements in the tree layer of the mature P.massoniana plantation was 46.09 kg/(hm^2·a),and the order of the annual net accumulation of different nutrient elements followed N>K>Ca>Mg>P;and the accumulation of 1 t of dry matter needed 6.37 kg of the five nutrients.[Conclusions]This study provides a scientific basis for the rational management of P.massoniana plantations,especially forest soil management.展开更多
[Objectives]This study was conducted to understand the carbon sequestration function of mature Pinus massoniana plantation in northwest Guangxi.[Methods]The carbon storage and distribution in a 26-year-old P.massonian...[Objectives]This study was conducted to understand the carbon sequestration function of mature Pinus massoniana plantation in northwest Guangxi.[Methods]The carbon storage and distribution in a 26-year-old P.massoniana plantation were investigated through biomass harvesting in Shankou Forestry Farm of Nandan County,Guangxi Province.[Results]The average carbon content of P.massoniana was 489.3 g/kg,and the carbon contents of different organs ranked from large to small as pine needles > trunks > trunk bark > roots > branches.The carbon contents of understory shrub layer,herb layer and litter layer were 453.0,425.6 and 482.5 g/kg,respectively.The soil organic carbon content in forestland varied from 6.20 to 32.15 g/kg,decreasing with the depth of the soil layer.The carbon storage of the mature P.massoniana plantation ecosystem was 232.13 t/hm^2,of which the tree layer,shrub layer,herb layer,litter layer and soil layer were 92.67,1.36,1.12 and 134.49 t/hm^2,respectively,which accounted for 39.92%,0.59%,0.48%,1.07% and 57.94% of the carbon storage of the whole ecosystem,respectively.The annual net productivity of the tree layer of the mature P.massoniana plantation was 10.36 t/(hm^2·a),the annual net carbon sequestration was 5.41 t/(hm^2·a),and the annual net CO2 absorption was 19.83 t/(hm^2·a).[Conclusions]This study provides basic data and scientific basis for rational evaluation of the ecological benefits of P.massoniana plantation in this area.展开更多
Authors analysed foliar nutrition data from the ICP Forests(International Co-operative Programme on the Assessment and Monitoring of Air Pollution on Forests)monitoring network in two neighbouring Central European cou...Authors analysed foliar nutrition data from the ICP Forests(International Co-operative Programme on the Assessment and Monitoring of Air Pollution on Forests)monitoring network in two neighbouring Central European countries:the CZ(Czech Republic)and SK(Slovakia).Authors evaluated altogether seven coniferous(six Norway spruce and one Scots pine)and six broadleaves(five European beech and one Sessile oak)in intensively monitored plots.The longest time series cover more than 20 years(1995-2017 in CZ;1995-2013 in SK).The data show a significant decrease of the concentration of major nutrients,mainly P and K.On roughly half of plots,the concentration of P is near or below the deficiency limit(1.2 g·kg-1),the concentration of K has dropped by 10%to 50%,especially in stands of broadleaves during the evaluated period.Over time P and K have shown significantly decreasing trends on one third of the evaluated coniferous plots and a similar situation has occurred on broadleaf plots.Both countries differ in Mg trends-there is a decrease of Mg concentration in needles in SK compared with Czech coniferous plots.On the other hand,in beech leaves there is a decrease of Mg in both countries,and in CZ the trend over time for Mg is significant.The observed changes in nutrition level with stable or slightly increasing N concentration and with a drop in phosphorus and base cations have led to nutrient imbalance,especially between N and P.展开更多
文摘Interior Alaska has a short growing season of 110 d.The knowledge of timings of crop flowering and maturity will provide the information for the agricultural decision making.In this study,six machine learning algorithms,namely Linear Discriminant Analysis(LDA),Support Vector Machines(SVMs),k-nearest neighbor(kNN),Naïve Bayes(NB),Recursive Partitioning and Regression Trees(RPART),and Random Forest(RF),were selected to forecast the timings of barley flowering and maturity based on the Alaska Crop Datasets and climate data from 1991 to 2016 in Fairbanks,Alaska.Among 32 models fit to forecast flowering time,two from LDA,12 from SVMs,four from NB,three from RF outperformed models from other algorithms with the highest accuracy.Models from kNN performed worst to forecast flowering time.Among 32 models fit to forecast maturity time,two models from LDA outperformed the models from other algorithms.Models from kNN and RPART performed worst to forecast maturity time.Models from machine learning methods also provided a variable importance explanation.In this study,four out of six algorithms gave the same variable importance order.Sowing date was the most important variable to forecast flowering but less important variable to forecast maturity.The daily maximum temperature may be more important than daily minimum temperature to fit flowering models while daily minimum temperature may be more important than daily maximum temperature to fit maturity models.The results indicate that models from machine learning provide a promising technique in forecasting the timings of flowering and maturity of barley.
基金Supported by Special Fund for Innovation-driven Development in Guangxi Zhuangzu Autonomous Region(GK AA17204087-11)Natural Science Foundation of China(31560206 31760201)
文摘[Objectives]This study was conducted to reveal the characteristics of nutrient absorption and accumulation in Pinus massoniana plantations in Northwestern Guangxi.[Methods]Based on field investigation and indoor analysis,the contents,accumulation and annual net accumulation of five nutrient elements(N,P,K,Ca and Mg)in a mature P.massoniana plantation(26-year-old)in Nandan County,Guangxi Province were studied.[Results]The contents of nutrient elements in different organs of the mature P.massoniana plantation were the highest in the leaves,followed by the bark,branch and root,and the lowest in the stem.In general,among the contents of the five elements in different organs,N content was the highest,followed by K or Ca,and P and Mg were the lowest.The total accumulation of nutrient elements in the 26-year-old mature P.massoniana plantation in northwestern Guangxi was 1 384.05 kg/hm^2.Among the different structural levels of the stand,the tree layer had the highest accumulation of nutrient elements,which was 1 198.41 kg/hm^2,accounting for 86.59%of the total accumulation of nutrients in the plantation,and the accumulation of nutrients in other layers from the largest to the smallest was the litter layer(91.97 kg/hm^2),herb layer(49.86 kg/hm^2)and shrub layer(43.92 kg/hm^2),accounting for 3.17%,3.60%and 6.64%of the total nutrient accumulation of the plantation,respectively.The annual net accumulation of nutrient elements in the tree layer of the mature P.massoniana plantation was 46.09 kg/(hm^2·a),and the order of the annual net accumulation of different nutrient elements followed N>K>Ca>Mg>P;and the accumulation of 1 t of dry matter needed 6.37 kg of the five nutrients.[Conclusions]This study provides a scientific basis for the rational management of P.massoniana plantations,especially forest soil management.
基金Supported by Special Fund for Innovation-driven Development in Guangxi Zhuangzu Autonomous Region(GK AA17204087-11)Natural Science Foundation of China(31560206 31760201)
文摘[Objectives]This study was conducted to understand the carbon sequestration function of mature Pinus massoniana plantation in northwest Guangxi.[Methods]The carbon storage and distribution in a 26-year-old P.massoniana plantation were investigated through biomass harvesting in Shankou Forestry Farm of Nandan County,Guangxi Province.[Results]The average carbon content of P.massoniana was 489.3 g/kg,and the carbon contents of different organs ranked from large to small as pine needles > trunks > trunk bark > roots > branches.The carbon contents of understory shrub layer,herb layer and litter layer were 453.0,425.6 and 482.5 g/kg,respectively.The soil organic carbon content in forestland varied from 6.20 to 32.15 g/kg,decreasing with the depth of the soil layer.The carbon storage of the mature P.massoniana plantation ecosystem was 232.13 t/hm^2,of which the tree layer,shrub layer,herb layer,litter layer and soil layer were 92.67,1.36,1.12 and 134.49 t/hm^2,respectively,which accounted for 39.92%,0.59%,0.48%,1.07% and 57.94% of the carbon storage of the whole ecosystem,respectively.The annual net productivity of the tree layer of the mature P.massoniana plantation was 10.36 t/(hm^2·a),the annual net carbon sequestration was 5.41 t/(hm^2·a),and the annual net CO2 absorption was 19.83 t/(hm^2·a).[Conclusions]This study provides basic data and scientific basis for rational evaluation of the ecological benefits of P.massoniana plantation in this area.
文摘基于遥感监测多品种玉米成熟度进而掌握最佳收获时机,对提高其产量和品质至关重要。该研究在玉米成熟阶段获取无人机多光谱影像,同步采集叶片叶绿素含量(chlorophyll content,C)、籽粒含水率(moisture content,M)、乳线占比(proportion of milk line,P)等地面实测数据,以此构建玉米成熟度指数(maize maturity index,MMI),从而定量表征玉米成熟度。通过MMI与植被指数构建回归模型和随机森林模型,验证MMI适用性,并分析无人机遥感对不同品种玉米成熟度的监测精度。结果表明:1)不同品种玉米的叶片叶绿素含量、籽粒含水率、乳线占比的变化速率均存在差异。2)MMI与所选植被指数的相关性均可达到0.01显著水平,其中与归一化植被指数(normalized difference vegetation index,NDVI)、转换叶绿素吸收率(transformed chlorophyll absorbtion ratio index,TCARI)相关性最高,相关系数均为0.87。3)该研究基于不同组合的数据集进行了模型验证,其中随机森林模型对MMI的估测精度最高,测试集决定系数(coefficient of determination,R^(2))为0.84,均方根误差(root mean squared error,RMSE)为8.77%,标准均方根误差(normalized root mean squared error,nRMSE)为12.05%。此外,随机森林模型对不同品种MMI的估测精度较好,京九青贮16精度最优,其R^(2)、RMSE、nRMSE为0.76、10.67%、15.88%,模型精度证明了可以利用无人机平台对不同品种玉米成熟度进行监测。研究结果可为多光谱无人机实时监测农田多品种玉米成熟度的动态变化提供参考。
基金the Czech Ministry of Agriculture,institutional support MZE-RO0118the Slovak Research and Development Agency under Contract No.APVV-18-0223.
文摘Authors analysed foliar nutrition data from the ICP Forests(International Co-operative Programme on the Assessment and Monitoring of Air Pollution on Forests)monitoring network in two neighbouring Central European countries:the CZ(Czech Republic)and SK(Slovakia).Authors evaluated altogether seven coniferous(six Norway spruce and one Scots pine)and six broadleaves(five European beech and one Sessile oak)in intensively monitored plots.The longest time series cover more than 20 years(1995-2017 in CZ;1995-2013 in SK).The data show a significant decrease of the concentration of major nutrients,mainly P and K.On roughly half of plots,the concentration of P is near or below the deficiency limit(1.2 g·kg-1),the concentration of K has dropped by 10%to 50%,especially in stands of broadleaves during the evaluated period.Over time P and K have shown significantly decreasing trends on one third of the evaluated coniferous plots and a similar situation has occurred on broadleaf plots.Both countries differ in Mg trends-there is a decrease of Mg concentration in needles in SK compared with Czech coniferous plots.On the other hand,in beech leaves there is a decrease of Mg in both countries,and in CZ the trend over time for Mg is significant.The observed changes in nutrition level with stable or slightly increasing N concentration and with a drop in phosphorus and base cations have led to nutrient imbalance,especially between N and P.