{
  "fetched_at": "2026-10-20T10:14:24Z",
  "source_url": "https://www.kaggle.com/competitions/6th-idss-ai-for-agriculture-competition-track1/data",
  "pages": [
    {
      "name": "data-description",
      "content": "File of Training data \n\nFile of Testing data\n\nYour solution should be a file excel containing two columns: 'Id' and 'EVo[mm]'\n!!! Do not put the RMSE values in the solution file, since it will be calculated automatically !!!",
      "isPublished": false,
      "hasIsPublished": false,
      "postTitle": "",
      "hasPostTitle": false,
      "mimeType": "",
      "hasMimeType": false
    },
    {
      "name": "Description",
      "content": "**Track 1: the problem of parameters prediction **\n\nWe propose the CLIMATE database (EV0_competition_IDSS.csv) in the folder\nwith the climate parameters including Ev0: evaporation from Gabes STATION AVFA – AgriDATA\n\n\tT : Air temperature [°C]\n\tP : Precipitation [mm]\n\tHR : Relative humidity [%]\n\tVV: Wind speed [m/s]\n\tRS : Solar radiation [W/m2]\n\tEv0 : Evapo-transpiration \n\nWe propose a system with the **5 parameters as inputs **and **EV0** will be the predicted parameter as **output**.\n\n**Step 1 Data pre-processing** Including the interpolation of the missing values of dataset, and the normalization. The last is used to eliminate the dimension influence between climate factors. Data normalization can speed up the gradient descend algorithm to find the optimal solution and possibly improve the prediction accuracy. \n\n**Step 2 **Input the preprocessing and normalized data into the model network with parameters randomly initialized. And then set the prediction step length, train errors by batching network. After that, compare the predicted value with the real value to calculate whether the iteration condition is satisfied. Thus, the error should descend to a certain degree, or the number of iterations is reached. \n\n**Step 3** Use the training sample to run the model through step 3, then input the test sample into the well-trained \n\n**Step 4** Plot the Variation curves of the input variables \n\n**Step 5** Calculate the metrics values Root-mean-square deviation (RMSE) of the parameters Ev0 which is predicted\nStep 6 Evaluate the trained classifier based on the test set. Plot the variation curves of the loss function.\nThe final evaluation will rely on the following metric\t**Root-mean-square error (RMSE)**\n**rmse = math.sqrt(mean_squared_error(y_test, pred))**\nRMSE is a frequently used measure of the differences between values (sample or population values) predicted by a model or an estimator and the values observed. The RMSE represents the square root of the second sample moment of the differences between predicted values and observed values or the quadratic mean of these differences.\n The RMSE of predicted values  (y hat) for times t of a regression's dependent variable  y  with variables observed over T times, is computed for T different predictions as the square root of the mean of the squares of the deviations: \n  \nAll documents will be sent to **cis.tn@ieee.org**\n\n \n \n",
      "isPublished": false,
      "hasIsPublished": false,
      "postTitle": "",
      "hasPostTitle": false,
      "mimeType": "",
      "hasMimeType": false
    },
    {
      "name": "Evaluation",
      "content": "Evaluation Metric\nThe evaluation metric for this competition is root-mean-square error (RMSE). The RMSE score, is a frequently used measure of the differences between values (sample or population values) predicted by a model or an estimator and the values observed. The RMSE score is given by:\n\n[https://en.wikipedia.org/wiki/Root-mean-square_deviation]()\n\nSubmission Format\nFor every unique combination in the dataset, submission files should contain two columns: Id and EVo[mm].\n\nThe file should have the following format:\nId (the same column index in the test set file) column and EVo[mm] column.\n\n",
      "isPublished": false,
      "hasIsPublished": false,
      "postTitle": "",
      "hasPostTitle": false,
      "mimeType": "",
      "hasMimeType": false
    },
    {
      "name": "rules",
      "content": "Our rules are:\n\n - Don't cheat!\n - Apply yourself!\n - Have fun!",
      "isPublished": false,
      "hasIsPublished": false,
      "postTitle": "",
      "hasPostTitle": false,
      "mimeType": "",
      "hasMimeType": false
    }
  ]
}